update,

vinniesniper-54816/task1/_lab/007-train-beach-test2/.gitignore

@@ -0,0 +1,2 @@
+*.txt
+*.vec

vinniesniper-54816/task1/_lab/007-train-beach-test2/README.md

@@ -0,0 +1,66 @@
+# OPENCV级联分类器训练
+
+## 1.收集样本
+
+### 正样本
+  - 转化成灰度（可用_RGBtoGray.py脚本）
+  - 转化成jpg格式（可用_BMP2JPG.py脚本）
+  - 分辨率20X20
+  - 从0开始按序号命名（可用_ReName.py脚本）
+### 负样本
+  - 转化成灰度（可用_RGBtoGray.py脚本）
+  - 转化成jpg格式（可用_BMP2JPG.py脚本）
+  - 分辨率随意
+  - 需要明显多于正样本
+  - 从0开始按序号命名（可用_ReName.py脚本）
+
+## 2.生成txt数据集路径表
+
+  - 生成文件（可用_GenTXT.py脚本）
+  - 拷贝到项目顶层目录（可用_copy.py脚本）
+
+## 3.生成正样本数据集（负样本数据在下一步用于训练）
+  - 编辑step1.py，根据自己的样本情况修改参数
+  - 执行step1.py脚本
+
+## 4.训练
+  - 编辑step2.py，根据自己的样本情况修改参数
+  - 执行step2.py脚本
+
+## 3.得到模型
+  - 进入xml文件夹，里面就有训练各个层数的模型
+
+## 5.示范
+
+ ```python
+import cv2
+
+# 读取待检测的图像
+image = cv2.imread('12.jpg')
+
+# 获取 XML 文件，加载人脸检测器
+faceCascade = cv2.CascadeClassifier('cascade.xml')
+
+# 色彩转换，转换为灰度图像
+gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
+
+# 调用函数 detectMultiScale
+faces = faceCascade.detectMultiScale(gray,scaleFactor = 1.15,minNeighbors = 5,minSize = (5,5))
+
+#print(faces)
+# 打印输出的测试结果
+print("发现{0}个人脸!".format(len(faces)))
+
+# 逐个标注人脸
+for(x,y,w,h) in faces:
+    cv2.rectangle(image,(x,y),(x+w,y+w),(0,255,0),2) #矩形标注
+    #cv2.circle(image,(int((x+x+w)/2),int((y+y+h)/2)),int(w/2),(0,255,0),2)
+    
+# 显示结果
+cv2.imshow("dect",image)
+# 保存检测结果
+cv2.imwrite("re.jpg",image)
+cv2.waitKey(0)
+cv2.destroyAllWindows()
+
+ ```

vinniesniper-54816/task1/_lab/007-train-beach-test2/clear.bat

@@ -0,0 +1,7 @@
+del neg.txt
+del pos.txt
+del pos.vec
+del .\\xml\\*
+del .\\negdata\\neg.txt
+del .\\posdata\\pos.txt
+

vinniesniper-54816/task1/_lab/007-train-beach-test2/clear.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+set -ex
+
+cd posdata
+    rm -rf *Zone*
+cd ..
+
+cd negdata
+    rm -rf *Zone*
+cd ..
+
+rm -rf *Zone*

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/.gitignore

@@ -0,0 +1,5 @@
+*.jpg
+*.png
+*.bmp
+*.gif
+*.webp

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/_GenTXT.py

@@ -0,0 +1,9 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+os.system("dir /b/s/p/w *.jpg > neg.txt")
+
+
+os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/_PNG2JPG.py

@@ -0,0 +1,26 @@
+import os
+from PIL import Image
+ 
+ 
+# 获取指定目录下的所有png图片
+def get_all_png_files(dir):
+    files_list = []
+    for root, dirs, files in os.walk(dir):
+        for file in files:
+            if os.path.splitext(file)[1] == '.png':
+                files_list.append(os.path.join(root, file))
+    return files_list
+ 
+ 
+# 批量转换png图片为jpg格式
+def png2jpg(files_list):
+    for file in files_list:
+        img = Image.open(file)
+        new_file = os.path.splitext(file)[0] + '.jpg'
+        img.convert('RGB').save(new_file)
+ 
+ 
+if __name__ == '__main__':
+    dir = './' #png图片目录
+    files_list = get_all_png_files(dir)
+    png2jpg(files_list)

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/_RGBtoGray.py

@@ -0,0 +1,26 @@
+# -*- coding:utf8 -*-
+import cv2
+import numpy as np 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+ 
+# 批量灰度化图片
+def GrayPic(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        img=cv2.imread(imgName)
+        gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
+        cv2.imwrite("gray"+imgName,gray)
+        
+        
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    GrayPic(srcImgPath)
+    
+    os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/_ReName.py

@@ -0,0 +1,27 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePic(srcImgPath)
+    
+    os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata.1/_copy.py

@@ -0,0 +1,8 @@
+# -*- coding:utf8 -*-
+import os
+
+
+os.system("copy .\\neg.txt ..\\")
+
+
+os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata/_GenTXT.py

@@ -0,0 +1,9 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+# os.system("dir /b/s/p/w *.jpg > neg.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > neg.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata/_copy.py

@@ -0,0 +1,8 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# os.system("copy .\\neg.txt ..\\")
+os.system("cp ./neg.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_all/_GenTXT.py

@@ -0,0 +1,9 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+# os.system("dir /b/s/p/w *.jpg > neg.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > neg.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_all/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_all/_copy.py

@@ -0,0 +1,8 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# os.system("copy .\\neg.txt ..\\")
+os.system("cp ./neg.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_wo_beach/6xx_flower_bing/find_dup.py

@@ -0,0 +1,25 @@
+import os
+import hashlib
+
+
+def find_dup(dir):
+    files = {}
+    for root, _, filenames in os.walk(dir):
+        for f in filenames:
+            file_path = os.path.join(root, f)
+            with open(file_path, "rb") as file:
+                file_hash = hashlib.md5(file.read()).hexdigest()
+            if file_hash in files:
+                files[file_hash].append(file_path)
+            else:
+                files[file_hash] = [file_path]
+
+    for file_hash, file_paths in files.items():
+        if len(file_paths) > 1:
+            print("dup:", file_hash)
+            for file_path in file_paths:
+                os.remove(file_path)
+
+
+if __name__ == "__main__":
+    find_dup("/home/logic/_wsl_workspace/comission-playlist/vinniesniper-54816/task1/_lab/003-crawler-bus/p/flower")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_wo_beach/_GenTXT.py

@@ -0,0 +1,9 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+# os.system("dir /b/s/p/w *.jpg > neg.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > neg.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_wo_beach/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/negdata_wo_beach/_copy.py

@@ -0,0 +1,8 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# os.system("copy .\\neg.txt ..\\")
+os.system("cp ./neg.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/notes.md

@@ -0,0 +1,37 @@
+### vnc
+
+host 192.168.10.21
+
+<http://192.168.10.21:6199/>
+
+work path
+/home/logic/_workspace/task-list/servers/logic-NUC8i5BEH/opencv-workdesk/001_monitor/src/007-test
+
+# test results
+
+| nPos  | nNeg  | nStage |  px   |  TT   | TT base |  FT   | FT base |                          remarks                           |
+| :---: | :---: | :----: | :---: | :---: | :-----: | :---: | :-----: | :--------------------------------------------------------: |
+|  300  |  900  |   15   |  24  |   2   |    2    |   7   |   14    | ongoing, i want to know if i increase px increase accuracy |
+|  200  |  900  |   15   |  100  |   2   |    2    |   7   |   14    | ongoing, i want to know if i increase px increase accuracy |
+|  200  |  900  |   15   |  24   |   2   |    2    |   7   |   14    |                                                            |
+|  100  |  300  |   15   |   x   |  33   |   142   |   x   |    x    |                                                            |
+
+```bash
+-numPos 100
+-numNeg 300
+-numStages 15
+```
+
+```bash
+count_good_result      : 33
+count_good_result_base : 99
+count_bad_result       : 142
+```
+
+### test with 100 posdata
+
+```bash
+count_good_result      : 33
+count_good_result_base : 99
+count_bad_result       : 142
+```

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/.gitignore

@@ -0,0 +1,5 @@
+*.jpg
+*.png
+*.bmp
+*.gif
+*.webp

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/_BMP2JPG.py

@@ -0,0 +1,16 @@
+import os
+from PIL import Image
+
+json_dir = "./"
+label_names = os.listdir(json_dir)
+label_dir = []
+
+for filename in label_names:
+    label_dir.append(os.path.join(json_dir,filename))
+
+for i,filename in enumerate(label_dir):
+
+    im = Image.open(filename)  # open ppm file
+
+    newname = label_names[i].split('.')[0] + '.jpg'  # new name for png file
+    im.save(os.path.join(json_dir,newname))

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/_GenTXT.py

@@ -0,0 +1,9 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+os.system("dir /b/s/p/w *.jpg > pos.txt")
+
+
+os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/_RGBtoGray.py

@@ -0,0 +1,26 @@
+# -*- coding:utf8 -*-
+import cv2
+import numpy as np 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+ 
+# 批量灰度化图片
+def GrayPic(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        img=cv2.imread(imgName)
+        gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
+        cv2.imwrite("gray"+imgName,gray)
+        
+        
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    GrayPic(srcImgPath)
+    
+    os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/_ReName.py

@@ -0,0 +1,27 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePic(srcImgPath)
+    
+    os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata.1/_copy.py

@@ -0,0 +1,8 @@
+# -*- coding:utf8 -*-
+import os
+
+
+os.system("copy .\\pos.txt ..\\")
+
+
+os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_100/_GenTXT.py

@@ -0,0 +1,10 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+#
+# os.system("dir /b/s/p/w *.jpg > pos.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > pos.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_100/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_100/_copy.py

@@ -0,0 +1,11 @@
+# -*- coding:utf8 -*-
+import os
+
+import platform
+
+# if platform.system() == "Windows":
+# os.system("copy .\\pos.txt ..\\")
+# else:
+os.system("cp ./pos.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_200/_GenTXT.py

@@ -0,0 +1,10 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+#
+# os.system("dir /b/s/p/w *.jpg > pos.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > pos.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_200/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_200/_copy.py

@@ -0,0 +1,11 @@
+# -*- coding:utf8 -*-
+import os
+
+import platform
+
+# if platform.system() == "Windows":
+# os.system("copy .\\pos.txt ..\\")
+# else:
+os.system("cp ./pos.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_400/_GenTXT.py

@@ -0,0 +1,10 @@
+# -*- coding:utf8 -*-
+import os
+
+
+# 生成路径列表文件
+#
+# os.system("dir /b/s/p/w *.jpg > pos.txt")
+os.system("find " + os.path.abspath(os.curdir) + " -name '*.jpg' > pos.txt")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_400/_ReName.py

@@ -0,0 +1,46 @@
+# -*- coding:utf8 -*-
+ 
+import os
+import re
+import shutil
+from pathlib2 import Path
+ 
+import string
+import random
+
+# 批量命名图片
+def renamePicWithRandomName(srcImgDir):
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        # 生成随机字符串
+        random_str = ''.join(random.sample(string.ascii_letters + string.digits, 32))
+        # 生成随机数字
+        random_int = str(random.randint(0, 10000))
+        # 生成新的图片名
+        newName = random_str + random_int + ".jpg"
+        # 重命名
+        print(f"prepare to rename {imgName} to {newName}")
+        item.rename(newName)
+
+
+ 
+# 批量命名图片
+def renamePic(srcImgDir):
+    i=0
+    for item in srcImgDir.rglob("*.jpg"):
+        # 获取图片名
+        imgName = item.name
+        newName = str(i)+".jpg"
+        i=i+1
+        # 重命名
+        print(f"prepare to rename {imgName}")
+        item.rename(newName)
+ 
+if __name__ == '__main__':
+
+    # 文件路径--跟代码同目录
+    srcImgPath = Path("./")
+    renamePicWithRandomName(srcImgPath)
+    renamePic(srcImgPath)
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/posdata_400/_copy.py

@@ -0,0 +1,11 @@
+# -*- coding:utf8 -*-
+import os
+
+import platform
+
+# if platform.system() == "Windows":
+# os.system("copy .\\pos.txt ..\\")
+# else:
+os.system("cp ./pos.txt ../")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/process_txt_files.py

@@ -0,0 +1,21 @@
+import os
+import sys
+
+def trim_last_newline(file_path):
+    with open(file_path, 'r+') as file:
+        file.seek(0, os.SEEK_END)
+        file.seek(file.tell() - 1, os.SEEK_SET)
+        file.truncate()
+
+def process_pos_file(width, height):
+    with open('pos.txt', 'r') as file:
+        data = file.read()
+    data = data.replace('.jpg', '.jpg 1 0 0 {} {}'.format(width, height))
+    with open('pos.txt', 'w') as file:
+        file.write(data)
+
+if __name__ == "__main__":
+    trim_last_newline('neg.txt')
+    trim_last_newline('pos.txt')
+    process_pos_file(sys.argv[1], sys.argv[1])
+

vinniesniper-54816/task1/_lab/007-train-beach-test2/slice_image/slice_image.py

@@ -0,0 +1,61 @@
+# write a pytohn code that will read a image named `helloworld.jpg`,
+# crop 20x20 pixels randomly
+# create a output folder named `output`,
+# save the cropped image in the output folder, and rename it to `helloworld_cropped.jpg`
+import os,sys
+import cv2
+import random
+
+crop_width = int(sys.argv[1])
+crop_height = int(sys.argv[2])
+no_files = int(sys.argv[3])
+no_slices = int(sys.argv[4])
+
+# remove all files in output before start
+for file in os.listdir('output'):
+    file_path = os.path.join('output', file)
+    try:
+        if os.path.isfile(file_path):
+            os.unlink(file_path)
+    except Exception as e:
+        print(e)
+
+# Read the image
+images = []
+for i in range(100, 199+1):
+    image = cv2.imread(f'_pool/{i}.jpg')
+    images.append(image)
+
+j = 0
+for _ in range(no_files):
+    # Randomly select a image from images
+    image = random.choice(images)
+    if image is None:
+        continue
+    height, width, _ = image.shape
+
+    # Generate random coordinates for cropping
+
+    x = random.randint(0, width - crop_width)
+    y = random.randint(0, height - crop_height)
+
+    # Crop the image
+    cropped_image = image[y:y+crop_height, x:x+crop_width]
+
+    for i in range(no_slices):
+        j+=1
+        # Generate random coordinates for cropping
+        x = random.randint(0, width - crop_width)
+        y = random.randint(0, height - crop_height)
+
+        # Crop the image
+        cropped_image = image[y:y+crop_height, x:x+crop_width]
+
+        # Create output directory if it doesn't exist
+        output_dir = 'output'
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+
+        # Save the cropped image
+        cv2.imwrite(os.path.join(output_dir, 'beach_{}.jpg'.format(j)), cropped_image)
+

vinniesniper-54816/task1/_lab/007-train-beach-test2/step1.py

@@ -0,0 +1,9 @@
+import os
+
+# 处理前要将pos.txt里面每行按"*.jpg 1 0 0 20 20"的格式修改，neg.txt不需要改格式
+# neg.txt和pos.txt里面末尾的空行要删去
+# neg.txt里面图片大小和数量可以不用特别指定，也不需要生成vec文件
+# os.system("opencv_createsamples.exe -vec pos.vec -info pos.txt -num 100 -w 20 -h 20")
+os.system("opencv_createsamples -info pos.txt -vec pos.vec  -num 100 -w 20 -h 20")
+
+# os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/step1.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+set -x
+
+rm -rf pos.vec
+
+opencv_createsamples \
+    -info pos.txt \
+    -vec pos.vec  \
+    -num 400 \
+    -w 24 \
+    -h 24

vinniesniper-54816/task1/_lab/007-train-beach-test2/step2.py

@@ -0,0 +1,15 @@
+import os
+
+# numPos和numNeg是训练时每一层的样本数，numPos可以小于vec中的数目（推荐），numNeg可以大于实际数目
+# maxFalseAlarmRate是训练时的FA，只有小于它才会进入下一层
+# 网上推荐numPos：numNeg=1：3
+# 正样本用vec描述，负样本用txt指明路径即可
+# xml目录需要自己提前创建
+# 训练时出现的列表中：N训练层数，HR命中率，FA警告（FA<maxFalseAlarmRate进入下一层）
+# 负样本不用指定图中:目标个数，Xmin,Ymin,Xmax,Ymax。训练时会自动resize
+# os.system("opencv_traincascade.exe -data xml -vec pos.vec -bg neg.txt -numPos 90 -numNeg 198 -numStages 20 -w 20 -h 20 -maxFalseAlarmRate 0.5 -mode ALL")
+os.system(
+    "opencv_traincascade -data xml -vec pos.vec -bg neg.txt -numPos 90 -numNeg 198 -numStages 20 -w 20 -h 20 -maxFalseAlarmRate 0.5 -mode ALL"
+)
+
+os.system("pause")

vinniesniper-54816/task1/_lab/007-train-beach-test2/step2_t1.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+set -x
+
+rm -rf xml_step2_t1/*.xml
+
+echo "clean done"
+
+opencv_traincascade \
+    -data xml_step2_t1 \
+    -vec pos.vec \
+    -bg neg.txt \
+    -numPos 200 \
+    -numNeg 900 \
+    -numStages 15 \
+    -numThreads 6 \
+    -maxFalseAlarmRate 0.5 \
+    -w 24 \
+    -h 24 \
+    -mode ALL
+
+# i want to check the maxFalseAlarmRate larger, i want to complete the 20 steps

vinniesniper-54816/task1/_lab/007-train-beach-test2/step2_t2.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+set -x
+
+rm -rf xml_step2_t2/*.xml
+
+echo "clean done"
+
+opencv_traincascade \
+    -data xml_step2_t2 \
+    -vec pos.vec \
+    -bg neg.txt \
+    -numPos 100 \
+    -numNeg 300 \
+    -numStages 15 \
+    -numThreads 6 \
+    -maxFalseAlarmRate 0.5 \
+    -w 24 \
+    -h 24 \
+    -mode ALL
+
+# i want to check the maxFalseAlarmRate larger, i want to complete the 20 steps

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/cascade.xml

@@ -0,0 +1,886 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>24</height>
+  <width>24</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>5</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>7</maxWeakCount>
+      <stageThreshold>-1.7381234169006348e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 42 -6.6492641053628176e-05</internalNodes>
+          <leafValues>
+            -4.4080603122711182e-01 -8.7339973449707031e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 -8.8723754743114114e-05</internalNodes>
+          <leafValues>
+            1.9089424610137939e-01 -5.6245493888854980e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 1.3553324970416725e-04</internalNodes>
+          <leafValues>
+            -2.8372088074684143e-01 4.7440573573112488e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 -8.3068051026202738e-05</internalNodes>
+          <leafValues>
+            4.1643595695495605e-01 -2.5597107410430908e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 38 3.4708289604168385e-05</internalNodes>
+          <leafValues>
+            -2.7539277076721191e-01 3.5162928700447083e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 -9.3893191660754383e-05</internalNodes>
+          <leafValues>
+            3.5791626572608948e-01 -2.2714814543724060e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 23 2.2262248676270247e-03</internalNodes>
+          <leafValues>
+            1.1294199526309967e-01 -7.6507872343063354e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>11</maxWeakCount>
+      <stageThreshold>-1.6598495244979858e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 4 -4.8109769821166992e-01</internalNodes>
+          <leafValues>
+            1.0526315867900848e-01 -7.9716712236404419e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 11 -5.8517290744930506e-04</internalNodes>
+          <leafValues>
+            6.8462952971458435e-02 -5.0622791051864624e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 50 -1.0241747077088803e-04</internalNodes>
+          <leafValues>
+            3.2471290230751038e-01 -2.8698831796646118e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 -7.7438657172024250e-05</internalNodes>
+          <leafValues>
+            2.9068928956985474e-01 -2.5499323010444641e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 57 8.6392770754173398e-05</internalNodes>
+          <leafValues>
+            -2.4163618683815002e-01 3.1127682328224182e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 51 -4.8747510300017893e-04</internalNodes>
+          <leafValues>
+            3.3194142580032349e-01 -2.4148719012737274e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 45 -3.4984733792953193e-04</internalNodes>
+          <leafValues>
+            3.3430024981498718e-01 -2.0615211129188538e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 6 -7.2770075348671526e-05</internalNodes>
+          <leafValues>
+            3.3973968029022217e-01 -2.3804998397827148e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 5.1059282850474119e-04</internalNodes>
+          <leafValues>
+            -2.3525027930736542e-01 3.2482597231864929e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 8 7.2948190791066736e-05</internalNodes>
+          <leafValues>
+            -2.5756925344467163e-01 2.8721740841865540e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 46 3.1126552494242787e-04</internalNodes>
+          <leafValues>
+            1.2545214593410492e-01 -5.9483408927917480e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>13</maxWeakCount>
+      <stageThreshold>-1.6800838708877563e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 0 -5.7484042644500732e-01</internalNodes>
+          <leafValues>
+            1.6949152573943138e-02 -8.0504584312438965e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 58 -4.0488965169060975e-05</internalNodes>
+          <leafValues>
+            3.0533956363797188e-02 -4.6860376000404358e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 -3.0882708961144090e-04</internalNodes>
+          <leafValues>
+            2.3413044214248657e-01 -2.4772895872592926e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 17 3.5320821916684508e-04</internalNodes>
+          <leafValues>
+            -2.2953721880912781e-01 2.7811151742935181e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 40 -1.4940250548534095e-04</internalNodes>
+          <leafValues>
+            2.9266229271888733e-01 -2.1112221479415894e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 56 5.3845089860260487e-04</internalNodes>
+          <leafValues>
+            1.4814524352550507e-01 -5.6251770257949829e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 31 -9.0648085460998118e-05</internalNodes>
+          <leafValues>
+            2.5625523924827576e-01 -2.6112335920333862e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 4.6937786042690277e-02</internalNodes>
+          <leafValues>
+            -1.3361711800098419e-01 3.7699964642524719e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 61 8.9822955487761647e-05</internalNodes>
+          <leafValues>
+            -2.2085568308830261e-01 2.8921762108802795e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 -1.3652653433382511e-03</internalNodes>
+          <leafValues>
+            -6.5572941303253174e-01 9.9191062152385712e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 49 -2.0287258666940033e-04</internalNodes>
+          <leafValues>
+            2.3724743723869324e-01 -2.7433085441589355e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 -9.5827679615467787e-05</internalNodes>
+          <leafValues>
+            3.1363451480865479e-01 -2.0591317117214203e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 2.7167059015482664e-03</internalNodes>
+          <leafValues>
+            1.1219248920679092e-01 -5.7561796903610229e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>18</maxWeakCount>
+      <stageThreshold>-1.7151796817779541e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 3 4.5185452699661255e-01</internalNodes>
+          <leafValues>
+            -7.9435026645660400e-01 9.0909093618392944e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 53 -1.1153056402690709e-04</internalNodes>
+          <leafValues>
+            -1.8190445378422737e-02 -4.5706674456596375e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 55 -5.9445615857839584e-02</internalNodes>
+          <leafValues>
+            -8.4759205579757690e-01 4.2014323174953461e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 -1.9031716510653496e-03</internalNodes>
+          <leafValues>
+            2.6653257012367249e-01 -1.9722880423069000e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 48 -2.2689405828714371e-02</internalNodes>
+          <leafValues>
+            -5.5508196353912354e-01 8.5192307829856873e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 2.9013486346229911e-04</internalNodes>
+          <leafValues>
+            -1.9824767112731934e-01 2.5166839361190796e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 24 -1.0892121121287346e-02</internalNodes>
+          <leafValues>
+            -8.4603714942932129e-01 7.6737448573112488e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 62 -1.2086516653653234e-04</internalNodes>
+          <leafValues>
+            2.4898171424865723e-01 -2.2065225243568420e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 47 5.8647326659411192e-04</internalNodes>
+          <leafValues>
+            1.0237761586904526e-01 -5.0767165422439575e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 65 1.0198650124948472e-04</internalNodes>
+          <leafValues>
+            -2.0923440158367157e-01 2.7771601080894470e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 -1.3687880709767342e-04</internalNodes>
+          <leafValues>
+            2.4269771575927734e-01 -2.0890320837497711e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 14 2.5607962161302567e-03</internalNodes>
+          <leafValues>
+            7.3428317904472351e-02 -6.7707967758178711e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 35 1.4267786173149943e-04</internalNodes>
+          <leafValues>
+            -2.4035653471946716e-01 1.9846367835998535e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 3.1099127954803407e-04</internalNodes>
+          <leafValues>
+            1.1868908256292343e-01 -4.5720916986465454e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 -3.7832668749615550e-04</internalNodes>
+          <leafValues>
+            2.7774146199226379e-01 -1.9452299177646637e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 3.0772056197747588e-04</internalNodes>
+          <leafValues>
+            -1.9172298908233643e-01 2.5773844122886658e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 54 -7.8460504300892353e-04</internalNodes>
+          <leafValues>
+            -4.6616023778915405e-01 1.1061295121908188e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 66 -3.9050173654686660e-05</internalNodes>
+          <leafValues>
+            2.6625639200210571e-01 -2.0826312899589539e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>20</maxWeakCount>
+      <stageThreshold>-1.6644383668899536e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 7 1.5868088603019714e-01</internalNodes>
+          <leafValues>
+            -7.8507792949676514e-01 1.</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 60 2.2785542532801628e-03</internalNodes>
+          <leafValues>
+            -1.3975608348846436e-01 -5.5399090051651001e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 59 -1.7553361249156296e-04</internalNodes>
+          <leafValues>
+            2.1543101966381073e-01 -2.2344003617763519e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 13 -2.5209598243236542e-04</internalNodes>
+          <leafValues>
+            -4.1684207320213318e-01 1.4877231419086456e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 6.6677283030003309e-05</internalNodes>
+          <leafValues>
+            -2.0591776072978973e-01 2.1735632419586182e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 43 4.6974859287729487e-05</internalNodes>
+          <leafValues>
+            -2.0965799689292908e-01 2.0866128802299500e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 67 -5.8246543630957603e-04</internalNodes>
+          <leafValues>
+            -5.6367623805999756e-01 1.0261350870132446e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 41 -4.7807942610234022e-04</internalNodes>
+          <leafValues>
+            2.5512722134590149e-01 -1.9863390922546387e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 44 3.6294147139415145e-04</internalNodes>
+          <leafValues>
+            -1.9265744090080261e-01 2.4188078939914703e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 64 -4.9593922449275851e-04</internalNodes>
+          <leafValues>
+            2.5136378407478333e-01 -2.0082153379917145e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 39 1.2481587473303080e-03</internalNodes>
+          <leafValues>
+            1.0286387056112289e-01 -5.4534602165222168e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 52 6.3730927649885416e-04</internalNodes>
+          <leafValues>
+            1.2975558638572693e-01 -3.8010969758033752e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 36 -1.9632575567811728e-03</internalNodes>
+          <leafValues>
+            2.4727308750152588e-01 -2.2092473506927490e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 3.6180335283279419e-01</internalNodes>
+          <leafValues>
+            -1.0383813083171844e-01 5.1680284738540649e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 -9.7403884865343571e-05</internalNodes>
+          <leafValues>
+            3.1365016102790833e-01 -1.9530841708183289e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 30 5.5112491827458143e-04</internalNodes>
+          <leafValues>
+            1.0141395777463913e-01 -5.1928257942199707e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 63 -6.2572164461016655e-04</internalNodes>
+          <leafValues>
+            2.5433585047721863e-01 -2.1775600314140320e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 -6.7526052589528263e-05</internalNodes>
+          <leafValues>
+            2.3972965776920319e-01 -2.3175013065338135e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 34 -3.0191906262189150e-04</internalNodes>
+          <leafValues>
+            -5.1444709300994873e-01 1.0752265155315399e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 19 1.2140336912125349e-04</internalNodes>
+          <leafValues>
+            -2.4228219687938690e-01 2.2440417110919952e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 1 24 19 -1.</_>
+        <_>
+          12 1 12 19 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 2 10 2 -1.</_>
+        <_>
+          5 2 5 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 2 24 3 -1.</_>
+        <_>
+          12 2 12 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 24 17 -1.</_>
+        <_>
+          8 5 8 17 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 7 24 13 -1.</_>
+        <_>
+          12 7 12 13 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 17 5 2 -1.</_>
+        <_>
+          0 18 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 0 2 2 -1.</_>
+        <_>
+          2 0 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 5 6 16 -1.</_>
+        <_>
+          4 5 3 16 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 10 2 1 -1.</_>
+        <_>
+          1 10 1 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 0 22 19 -1.</_>
+        <_>
+          13 0 11 19 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 10 4 2 -1.</_>
+        <_>
+          2 10 4 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 8 12 2 -1.</_>
+        <_>
+          6 8 6 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 3 2 4 -1.</_>
+        <_>
+          4 3 1 2 2.</_>
+        <_>
+          5 5 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 4 2 2 -1.</_>
+        <_>
+          4 4 1 1 2.</_>
+        <_>
+          5 5 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 6 2 5 -1.</_>
+        <_>
+          5 6 1 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 11 6 7 -1.</_>
+        <_>
+          8 11 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 19 1 3 -1.</_>
+        <_>
+          4 20 1 1 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 19 1 4 -1.</_>
+        <_>
+          5 19 1 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 4 1 -1.</_>
+        <_>
+          7 0 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 6 1 4 -1.</_>
+        <_>
+          5 7 1 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 6 3 2 -1.</_>
+        <_>
+          7 6 1 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 11 4 6 -1.</_>
+        <_>
+          8 11 2 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 23 2 1 -1.</_>
+        <_>
+          7 23 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 2 4 -1.</_>
+        <_>
+          7 1 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 15 2 -1.</_>
+        <_>
+          7 2 15 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 22 2 1 -1.</_>
+        <_>
+          8 22 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 2 2 -1.</_>
+        <_>
+          9 0 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 1 9 4 -1.</_>
+        <_>
+          8 2 9 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 3 3 10 -1.</_>
+        <_>
+          9 3 1 10 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 20 2 1 -1.</_>
+        <_>
+          9 20 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 1 1 3 -1.</_>
+        <_>
+          9 2 1 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 0 1 2 -1.</_>
+        <_>
+          10 0 1 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 3 2 2 -1.</_>
+        <_>
+          10 3 1 1 2.</_>
+        <_>
+          11 4 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 13 2 1 -1.</_>
+        <_>
+          11 13 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 4 2 2 -1.</_>
+        <_>
+          11 4 1 1 2.</_>
+        <_>
+          12 5 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 0 3 6 -1.</_>
+        <_>
+          13 0 1 6 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 1 12 5 -1.</_>
+        <_>
+          16 1 4 5 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 2 1 2 -1.</_>
+        <_>
+          12 2 1 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 3 4 1 -1.</_>
+        <_>
+          13 3 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 10 3 3 -1.</_>
+        <_>
+          13 10 1 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 18 2 2 -1.</_>
+        <_>
+          13 18 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 20 4 3 -1.</_>
+        <_>
+          14 20 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 5 2 1 -1.</_>
+        <_>
+          14 5 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 20 4 1 -1.</_>
+        <_>
+          14 20 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 20 4 4 -1.</_>
+        <_>
+          15 20 2 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 21 11 2 -1.</_>
+        <_>
+          13 22 11 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 1 2 2 -1.</_>
+        <_>
+          14 1 1 1 2.</_>
+        <_>
+          15 2 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 4 1 3 -1.</_>
+        <_>
+          14 5 1 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 6 6 18 -1.</_>
+        <_>
+          14 6 3 9 2.</_>
+        <_>
+          17 15 3 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 11 4 2 -1.</_>
+        <_>
+          14 11 4 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 15 2 2 -1.</_>
+        <_>
+          15 15 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 9 9 1 -1.</_>
+        <_>
+          18 9 3 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 13 4 3 -1.</_>
+        <_>
+          15 14 4 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 18 2 3 -1.</_>
+        <_>
+          16 18 1 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 6 3 2 -1.</_>
+        <_>
+          17 6 1 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          17 2 3 14 -1.</_>
+        <_>
+          17 9 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          17 4 2 2 -1.</_>
+        <_>
+          17 4 1 1 2.</_>
+        <_>
+          18 5 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 9 3 2 -1.</_>
+        <_>
+          19 9 1 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 0 2 1 -1.</_>
+        <_>
+          20 0 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 0 2 7 -1.</_>
+        <_>
+          20 0 1 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 2 4 12 -1.</_>
+        <_>
+          19 2 2 6 2.</_>
+        <_>
+          21 8 2 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 4 1 4 -1.</_>
+        <_>
+          19 6 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 6 2 2 -1.</_>
+        <_>
+          19 7 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          20 2 3 4 -1.</_>
+        <_>
+          20 4 3 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          20 12 4 4 -1.</_>
+        <_>
+          22 12 2 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          21 6 1 2 -1.</_>
+        <_>
+          21 7 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          21 23 2 1 -1.</_>
+        <_>
+          22 23 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          22 9 2 2 -1.</_>
+        <_>
+          22 9 1 1 2.</_>
+        <_>
+          23 10 1 1 2.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/cascade_working_example.xml

@@ -0,0 +1,544 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>12</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-2.0792216528207064e-03</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 23 3.5195697098970413e-02</internalNodes>
+          <leafValues>
+            -9.7000002861022949e-01 9.5833331346511841e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 4.9420498311519623e-02</internalNodes>
+          <leafValues>
+            -9.3253821134567261e-01 9.6792078018188477e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2283716201782227e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 2.1136376261711121e-01</internalNodes>
+          <leafValues>
+            -8.8292682170867920e-01 7.6744186878204346e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 -3.6786209791898727e-02</internalNodes>
+          <leafValues>
+            6.4631646871566772e-01 -8.5865759849548340e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 8.2553006708621979e-02</internalNodes>
+          <leafValues>
+            -9.6414572000503540e-01 5.1321285963058472e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.2522403001785278e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 34 -7.0488560013473034e-03</internalNodes>
+          <leafValues>
+            4.6428570151329041e-01 -9.0625000000000000e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 2.0252991467714310e-02</internalNodes>
+          <leafValues>
+            -9.2222303152084351e-01 3.8102594017982483e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2258527278900146e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 35 2.7621425688266754e-02</internalNodes>
+          <leafValues>
+            -9.3296086788177490e-01 2.7536231279373169e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 2.4644609540700912e-02</internalNodes>
+          <leafValues>
+            -7.8042775392532349e-01 5.6246817111968994e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 4.4026337563991547e-02</internalNodes>
+          <leafValues>
+            -7.2078734636306763e-01 5.9029269218444824e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.1094360351562500e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 13 5.6299664080142975e-02</internalNodes>
+          <leafValues>
+            -8.5567009449005127e-01 3.3333334326744080e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 2.0412717014551163e-02</internalNodes>
+          <leafValues>
+            -6.9705963134765625e-01 6.2128168344497681e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 3.3632911741733551e-02</internalNodes>
+          <leafValues>
+            -7.4570971727371216e-01 6.2287092208862305e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-1.0068651437759399e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 14 2.7963671088218689e-01</internalNodes>
+          <leafValues>
+            -8.6885243654251099e-01 1.6923077404499054e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 1.2323195114731789e-02</internalNodes>
+          <leafValues>
+            -7.9252362251281738e-01 3.5135197639465332e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 1.1619093269109726e-01</internalNodes>
+          <leafValues>
+            -8.5458588600158691e-01 4.3786722421646118e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 1.1368356645107269e-02</internalNodes>
+          <leafValues>
+            -8.9688044786453247e-01 3.6522126197814941e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.4377774000167847e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 17 2.8343785554170609e-02</internalNodes>
+          <leafValues>
+            -7.5813955068588257e-01 4.5454546809196472e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 -6.7780455574393272e-03</internalNodes>
+          <leafValues>
+            6.8800747394561768e-01 -5.7961523532867432e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 -9.6869543194770813e-03</internalNodes>
+          <leafValues>
+            5.2493661642074585e-01 -8.1870794296264648e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.8824944496154785e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 8 2.2776421904563904e-01</internalNodes>
+          <leafValues>
+            -7.8431373834609985e-01 2.7272728085517883e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 4 -1.3495892286300659e-01</internalNodes>
+          <leafValues>
+            3.2428205013275146e-01 -8.6097669601440430e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.8578220605850220e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 31 3.1056167557835579e-02</internalNodes>
+          <leafValues>
+            -7.7464789152145386e-01 4.8571428656578064e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.3904092609882355e-02</internalNodes>
+          <leafValues>
+            -7.8261238336563110e-01 4.7452750802040100e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 24 5.9338808059692383e-02</internalNodes>
+          <leafValues>
+            -6.1228525638580322e-01 5.7147806882858276e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2791478633880615e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 11 -1.5193784609436989e-02</internalNodes>
+          <leafValues>
+            -6.0240965336561203e-02 -8.6666667461395264e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 3 1.2929022312164307e-01</internalNodes>
+          <leafValues>
+            -7.7955096960067749e-01 2.7296727895736694e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 30 2.4830256006680429e-04</internalNodes>
+          <leafValues>
+            -8.2253754138946533e-01 3.6706984043121338e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-9.7741711139678955e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 36 -7.1106562390923500e-03</internalNodes>
+          <leafValues>
+            7.4074074625968933e-02 -7.8350514173507690e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 1.0002901777625084e-02</internalNodes>
+          <leafValues>
+            -9.6380352973937988e-01 1.2861841917037964e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 -1.1527233757078648e-02</internalNodes>
+          <leafValues>
+            3.1283980607986450e-01 -7.8981834650039673e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 7.7132084406912327e-03</internalNodes>
+          <leafValues>
+            -9.2314887046813965e-01 3.5634875297546387e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 -2.8069035615772009e-03</internalNodes>
+          <leafValues>
+            3.7375229597091675e-01 -7.4664002656936646e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.3949387073516846e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 19 4.9728322774171829e-03</internalNodes>
+          <leafValues>
+            -7.8894472122192383e-01 1.8367347121238708e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 8.1018730998039246e-03</internalNodes>
+          <leafValues>
+            -7.9892826080322266e-01 2.1818427741527557e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 9.7033903002738953e-03</internalNodes>
+          <leafValues>
+            -5.7855868339538574e-01 4.4443655014038086e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 -6.7393705248832703e-02</internalNodes>
+          <leafValues>
+            6.7329019308090210e-01 -4.4816955924034119e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 3.2395221292972565e-02</internalNodes>
+          <leafValues>
+            -8.7441539764404297e-01 4.0108311176300049e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 12 6 -1.</_>
+        <_>
+          6 0 6 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 7 20 -1.</_>
+        <_>
+          0 5 7 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 9 -1.</_>
+        <_>
+          0 3 20 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 2 16 -1.</_>
+        <_>
+          1 4 1 16 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 20 12 -1.</_>
+        <_>
+          0 7 20 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 6 9 -1.</_>
+        <_>
+          0 8 6 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 6 20 12 -1.</_>
+        <_>
+          10 6 10 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 12 3 8 -1.</_>
+        <_>
+          0 16 3 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 8 6 -1.</_>
+        <_>
+          2 14 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 15 3 -1.</_>
+        <_>
+          1 3 15 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 16 3 -1.</_>
+        <_>
+          1 3 16 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 5 6 -1.</_>
+        <_>
+          1 6 5 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 18 16 -1.</_>
+        <_>
+          1 7 18 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 3 16 1 -1.</_>
+        <_>
+          6 3 8 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 5 6 2 -1.</_>
+        <_>
+          4 7 2 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 9 6 9 -1.</_>
+        <_>
+          4 9 2 9 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 0 1 12 -1.</_>
+        <_>
+          3 6 1 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 2 6 2 -1.</_>
+        <_>
+          3 2 3 1 2.</_>
+        <_>
+          6 3 3 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 16 15 3 -1.</_>
+        <_>
+          9 17 5 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 4 3 -1.</_>
+        <_>
+          8 0 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 16 6 3 -1.</_>
+        <_>
+          6 17 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 6 13 -1.</_>
+        <_>
+          9 0 2 13 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 2 6 15 -1.</_>
+        <_>
+          9 2 2 15 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 2 -1.</_>
+        <_>
+          9 3 2 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 7 6 6 -1.</_>
+        <_>
+          9 9 2 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 4 6 -1.</_>
+        <_>
+          6 2 4 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 1 6 14 -1.</_>
+        <_>
+          9 1 3 7 2.</_>
+        <_>
+          12 8 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 3 9 15 -1.</_>
+        <_>
+          10 8 9 5 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 6 4 2 -1.</_>
+        <_>
+          12 6 2 1 2.</_>
+        <_>
+          14 7 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 10 8 6 -1.</_>
+        <_>
+          14 10 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 1 6 8 -1.</_>
+        <_>
+          12 3 6 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 4 1 -1.</_>
+        <_>
+          15 3 2 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 6 3 -1.</_>
+        <_>
+          14 3 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 3 2 8 -1.</_>
+        <_>
+          16 7 2 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 18 4 2 -1.</_>
+        <_>
+          18 18 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 0 1 20 -1.</_>
+        <_>
+          18 5 1 10 2.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/sanity_test.py

@@ -0,0 +1,127 @@
+import cv2
+import os,sys
+
+count_good_result = 0
+count_good_result_base = 0
+count_bad_result = 0
+count_bad_result_base = 0
+
+total_test_run = 0
+
+bad_result_African = 0
+bad_result_Beach = 0
+bad_result_Building = 0
+bad_result_Bus = 0
+bad_result_Dinosaur = 0
+bad_result_Dish = 0
+bad_result_Elephant = 0
+bad_result_Flower = 0
+bad_result_Horse = 0
+bad_result_Mountain = 0
+
+# 获取 XML 文件，加载人脸检测器
+faceCascade = cv2.CascadeClassifier("cascade.xml")
+
+# remove all jpg files in iut_re folder
+for f in os.listdir("iut_re"):
+    if f.endswith(".jpg"):
+        os.remove(os.path.join("iut_re", f))
+
+image_set = []
+for f in os.listdir("iut"):
+    if f.endswith(".jpg"):
+        file_name = os.path.join("iut", f)
+        image_set.append([cv2.imread(file_name), file_name])
+
+
+import random
+
+for i in range(len(image_set)):
+    if random.randint(1,20) == 1:
+        do_test = True
+    else:
+        do_test = False
+
+    if (do_test):
+        image = image_set[i][0]
+        file_name = image_set[i][1]
+        print(file_name)
+
+        re_file_name = file_name.replace(".jpg","_re.jpg").replace('iut/', 'iut_re/')
+        # 色彩转换，转换为灰度图像
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+        # 调用函数 detectMultiScale
+        faces = faceCascade.detectMultiScale(gray, scaleFactor=1.15, minNeighbors=5, minSize=(5, 5))
+
+        # print(faces)
+        # 打印输出的测试结果
+        # print("found {0} face in {1}".format(len(faces), os.path.basename(file_name)))
+        # print((re_file_name, len(faces)))
+
+        total_test_run += 1
+        result = os.path.basename(file_name).replace('.jpg','')
+
+        if (int(result) > 100 and int(result) < 200):
+            count_good_result_base += 1
+            if (len(faces) > 0):
+                count_good_result += 1
+        else:
+            count_bad_result_base +=1
+            if (len(faces) > 0):
+                count_bad_result += 1
+
+                if (int(result) >= 0 and int(result) < 100):
+                    bad_result_African += 1
+                elif (int(result) >= 100 and int(result) < 200):
+                    bad_result_Beach += 1
+                elif (int(result) >= 200 and int(result) < 300):
+                    bad_result_Building += 1
+                elif (int(result) >= 300 and int(result) < 400):
+                    bad_result_Bus += 1
+                elif (int(result) >= 400 and int(result) < 500):
+                    bad_result_Dinosaur += 1
+                elif (int(result) >= 500 and int(result) < 600):
+                    bad_result_Elephant += 1
+                elif (int(result) >= 600 and int(result) < 700):
+                    bad_result_Flower += 1
+                elif (int(result) >= 700 and int(result) < 800):
+                    bad_result_Horse += 1
+                elif (int(result) >= 800 and int(result) < 900):
+                    bad_result_Mountain += 1
+                elif (int(result) >= 900 and int(result) < 1000):
+                    bad_result_Dish += 1
+
+
+        # 逐个标注人脸
+        for x, y, w, h in faces:
+            cv2.rectangle(image, (x, y), (x + w, y + w), (0, 255, 0), 2)  # 矩形标注
+            # cv2.circle(image,(int((x+x+w)/2),int((y+y+h)/2)),int(w/2),(0,255,0),2)
+
+        if (len(faces) > 0):
+            # 显示结果
+            # cv2.imshow("dect", image)
+            # 保存检测结果
+            cv2.imwrite(re_file_name, image)
+            # cv2.waitKey(0)
+            # cv2.destroyAllWindows()
+
+print("count_good_result                            : "+ str(count_good_result))
+print('count_good_result_base                       : '+ str(count_good_result_base))
+print('count_bad_result                             : '+ str(count_bad_result))
+print('count_bad_result_base                        : '+ str(count_bad_result_base))
+
+print('bad result drill down')
+print('')
+print('bad_result_African                           : '+ str(bad_result_African))
+print('bad_result_Beach                             : '+ str(bad_result_Beach))
+print('bad_result_Building                          : '+ str(bad_result_Building))
+print('bad_result_Bus                               : '+ str(bad_result_Bus))
+print('bad_result_Dinosaur                          : '+ str(bad_result_Dinosaur))
+print('bad_result_Dish                              : '+ str(bad_result_Dish))
+print('bad_result_Elephant                          : '+ str(bad_result_Elephant))
+print('bad_result_Flower                            : '+ str(bad_result_Flower))
+print('bad_result_Horse                             : '+ str(bad_result_Horse))
+print('bad_result_Mountain                          : '+ str(bad_result_Mountain))
+
+print('total test run (good base + bad base)        : '+ str(total_test_run))

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/sanity_test.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+set -ex
+
+python ./sanity_test.py

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/test.py

@@ -0,0 +1,120 @@
+import cv2
+import os,sys
+
+count_good_result = 0
+count_good_result_base = 0
+count_bad_result = 0
+count_bad_result_base = 0
+
+total_test_run = 0
+
+bad_result_African = 0
+bad_result_Beach = 0
+bad_result_Building = 0
+bad_result_Bus = 0
+bad_result_Dinosaur = 0
+bad_result_Dish = 0
+bad_result_Elephant = 0
+bad_result_Flower = 0
+bad_result_Horse = 0
+bad_result_Mountain = 0
+
+# 获取 XML 文件，加载人脸检测器
+faceCascade = cv2.CascadeClassifier("cascade.xml")
+
+# remove all jpg files in iut_re folder
+for f in os.listdir("iut_re"):
+    if f.endswith(".jpg"):
+        os.remove(os.path.join("iut_re", f))
+
+image_set = []
+for f in os.listdir("iut"):
+    if f.endswith(".jpg"):
+        file_name = os.path.join("iut", f)
+        image_set.append([cv2.imread(file_name), file_name])
+
+
+for i in range(len(image_set)):
+    image = image_set[i][0]
+    file_name = image_set[i][1]
+    print(file_name)
+
+    re_file_name = file_name.replace(".jpg","_re.jpg").replace('iut/', 'iut_re/')
+    # 色彩转换，转换为灰度图像
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+    # 调用函数 detectMultiScale
+    faces = faceCascade.detectMultiScale(gray, scaleFactor=1.15, minNeighbors=5, minSize=(5, 5))
+
+    # print(faces)
+    # 打印输出的测试结果
+    # print("found {0} face in {1}".format(len(faces), os.path.basename(file_name)))
+    # print((re_file_name, len(faces)))
+
+    total_test_run += 1
+    result = os.path.basename(file_name).replace('.jpg','')
+
+    if (int(result) > 100 and int(result) < 200):
+        count_good_result_base += 1
+        if (len(faces) > 0):
+            count_good_result += 1
+    else:
+        count_bad_result_base +=1
+        if (int(result) >= 0 and int(result) < 100):
+            bad_result_African += 1
+        elif (int(result) >= 100 and int(result) < 200):
+            bad_result_Beach += 1
+        elif (int(result) >= 200 and int(result) < 300):
+            bad_result_Building += 1
+        elif (int(result) >= 300 and int(result) < 400):
+            bad_result_Bus += 1
+        elif (int(result) >= 400 and int(result) < 500):
+            bad_result_Dinosaur += 1
+        elif (int(result) >= 500 and int(result) < 600):
+            bad_result_Elephant += 1
+        elif (int(result) >= 600 and int(result) < 700):
+            bad_result_Flower += 1
+        elif (int(result) >= 700 and int(result) < 800):
+            bad_result_Horse += 1
+        elif (int(result) >= 800 and int(result) < 900):
+            bad_result_Mountain += 1
+        elif (int(result) >= 900 and int(result) < 1000):
+            bad_result_Dish += 1
+
+
+        if (len(faces) > 0):
+            count_bad_result += 1
+
+
+    # 逐个标注人脸
+    for x, y, w, h in faces:
+        cv2.rectangle(image, (x, y), (x + w, y + w), (0, 255, 0), 2)  # 矩形标注
+        # cv2.circle(image,(int((x+x+w)/2),int((y+y+h)/2)),int(w/2),(0,255,0),2)
+
+    if (len(faces) > 0):
+        # 显示结果
+        # cv2.imshow("dect", image)
+        # 保存检测结果
+        cv2.imwrite(re_file_name, image)
+        # cv2.waitKey(0)
+        # cv2.destroyAllWindows()
+
+print("count_good_result      : "+ str(count_good_result))
+print('count_good_result_base : '+ str(count_good_result_base))
+print('count_bad_result       : '+ str(count_bad_result))
+print('count_bad_result_base  : '+ str(count_bad_result_base))
+
+print('bad result drill down')
+print('')
+print('bad_result_African     : '+ str(bad_result_African))
+print('bad_result_Beach       : '+ str(bad_result_Beach))
+print('bad_result_Building    : '+ str(bad_result_Building))
+print('bad_result_Bus         : '+ str(bad_result_Bus))
+print('bad_result_Dinosaur    : '+ str(bad_result_Dinosaur))
+print('bad_result_Dish        : '+ str(bad_result_Dish))
+print('bad_result_Elephant    : '+ str(bad_result_Elephant))
+print('bad_result_Flower      : '+ str(bad_result_Flower))
+print('bad_result_Horse       : '+ str(bad_result_Horse))
+print('bad_result_Mountain    : '+ str(bad_result_Mountain))
+
+print('total test run         : '+ str(total_test_run))

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/test.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+set -ex
+
+python ./test.py

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/beach_test/test_w.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+set -ex
+
+npx nodemon --ext xml --exec "python ./test.py"

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test/cascade.xml

@@ -0,0 +1,544 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>12</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-2.0792216528207064e-03</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 23 3.5195697098970413e-02</internalNodes>
+          <leafValues>
+            -9.7000002861022949e-01 9.5833331346511841e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 4.9420498311519623e-02</internalNodes>
+          <leafValues>
+            -9.3253821134567261e-01 9.6792078018188477e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2283716201782227e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 2.1136376261711121e-01</internalNodes>
+          <leafValues>
+            -8.8292682170867920e-01 7.6744186878204346e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 -3.6786209791898727e-02</internalNodes>
+          <leafValues>
+            6.4631646871566772e-01 -8.5865759849548340e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 8.2553006708621979e-02</internalNodes>
+          <leafValues>
+            -9.6414572000503540e-01 5.1321285963058472e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.2522403001785278e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 34 -7.0488560013473034e-03</internalNodes>
+          <leafValues>
+            4.6428570151329041e-01 -9.0625000000000000e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 2.0252991467714310e-02</internalNodes>
+          <leafValues>
+            -9.2222303152084351e-01 3.8102594017982483e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2258527278900146e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 35 2.7621425688266754e-02</internalNodes>
+          <leafValues>
+            -9.3296086788177490e-01 2.7536231279373169e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 2.4644609540700912e-02</internalNodes>
+          <leafValues>
+            -7.8042775392532349e-01 5.6246817111968994e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 4.4026337563991547e-02</internalNodes>
+          <leafValues>
+            -7.2078734636306763e-01 5.9029269218444824e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.1094360351562500e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 13 5.6299664080142975e-02</internalNodes>
+          <leafValues>
+            -8.5567009449005127e-01 3.3333334326744080e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 2.0412717014551163e-02</internalNodes>
+          <leafValues>
+            -6.9705963134765625e-01 6.2128168344497681e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 3.3632911741733551e-02</internalNodes>
+          <leafValues>
+            -7.4570971727371216e-01 6.2287092208862305e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-1.0068651437759399e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 14 2.7963671088218689e-01</internalNodes>
+          <leafValues>
+            -8.6885243654251099e-01 1.6923077404499054e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 1.2323195114731789e-02</internalNodes>
+          <leafValues>
+            -7.9252362251281738e-01 3.5135197639465332e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 1.1619093269109726e-01</internalNodes>
+          <leafValues>
+            -8.5458588600158691e-01 4.3786722421646118e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 1.1368356645107269e-02</internalNodes>
+          <leafValues>
+            -8.9688044786453247e-01 3.6522126197814941e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.4377774000167847e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 17 2.8343785554170609e-02</internalNodes>
+          <leafValues>
+            -7.5813955068588257e-01 4.5454546809196472e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 -6.7780455574393272e-03</internalNodes>
+          <leafValues>
+            6.8800747394561768e-01 -5.7961523532867432e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 -9.6869543194770813e-03</internalNodes>
+          <leafValues>
+            5.2493661642074585e-01 -8.1870794296264648e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.8824944496154785e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 8 2.2776421904563904e-01</internalNodes>
+          <leafValues>
+            -7.8431373834609985e-01 2.7272728085517883e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 4 -1.3495892286300659e-01</internalNodes>
+          <leafValues>
+            3.2428205013275146e-01 -8.6097669601440430e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.8578220605850220e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 31 3.1056167557835579e-02</internalNodes>
+          <leafValues>
+            -7.7464789152145386e-01 4.8571428656578064e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.3904092609882355e-02</internalNodes>
+          <leafValues>
+            -7.8261238336563110e-01 4.7452750802040100e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 24 5.9338808059692383e-02</internalNodes>
+          <leafValues>
+            -6.1228525638580322e-01 5.7147806882858276e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2791478633880615e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 11 -1.5193784609436989e-02</internalNodes>
+          <leafValues>
+            -6.0240965336561203e-02 -8.6666667461395264e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 3 1.2929022312164307e-01</internalNodes>
+          <leafValues>
+            -7.7955096960067749e-01 2.7296727895736694e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 30 2.4830256006680429e-04</internalNodes>
+          <leafValues>
+            -8.2253754138946533e-01 3.6706984043121338e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-9.7741711139678955e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 36 -7.1106562390923500e-03</internalNodes>
+          <leafValues>
+            7.4074074625968933e-02 -7.8350514173507690e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 1.0002901777625084e-02</internalNodes>
+          <leafValues>
+            -9.6380352973937988e-01 1.2861841917037964e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 -1.1527233757078648e-02</internalNodes>
+          <leafValues>
+            3.1283980607986450e-01 -7.8981834650039673e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 7.7132084406912327e-03</internalNodes>
+          <leafValues>
+            -9.2314887046813965e-01 3.5634875297546387e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 -2.8069035615772009e-03</internalNodes>
+          <leafValues>
+            3.7375229597091675e-01 -7.4664002656936646e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.3949387073516846e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 19 4.9728322774171829e-03</internalNodes>
+          <leafValues>
+            -7.8894472122192383e-01 1.8367347121238708e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 8.1018730998039246e-03</internalNodes>
+          <leafValues>
+            -7.9892826080322266e-01 2.1818427741527557e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 9.7033903002738953e-03</internalNodes>
+          <leafValues>
+            -5.7855868339538574e-01 4.4443655014038086e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 -6.7393705248832703e-02</internalNodes>
+          <leafValues>
+            6.7329019308090210e-01 -4.4816955924034119e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 3.2395221292972565e-02</internalNodes>
+          <leafValues>
+            -8.7441539764404297e-01 4.0108311176300049e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 12 6 -1.</_>
+        <_>
+          6 0 6 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 7 20 -1.</_>
+        <_>
+          0 5 7 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 9 -1.</_>
+        <_>
+          0 3 20 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 2 16 -1.</_>
+        <_>
+          1 4 1 16 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 20 12 -1.</_>
+        <_>
+          0 7 20 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 6 9 -1.</_>
+        <_>
+          0 8 6 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 6 20 12 -1.</_>
+        <_>
+          10 6 10 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 12 3 8 -1.</_>
+        <_>
+          0 16 3 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 8 6 -1.</_>
+        <_>
+          2 14 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 15 3 -1.</_>
+        <_>
+          1 3 15 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 16 3 -1.</_>
+        <_>
+          1 3 16 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 5 6 -1.</_>
+        <_>
+          1 6 5 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 18 16 -1.</_>
+        <_>
+          1 7 18 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 3 16 1 -1.</_>
+        <_>
+          6 3 8 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 5 6 2 -1.</_>
+        <_>
+          4 7 2 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 9 6 9 -1.</_>
+        <_>
+          4 9 2 9 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 0 1 12 -1.</_>
+        <_>
+          3 6 1 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 2 6 2 -1.</_>
+        <_>
+          3 2 3 1 2.</_>
+        <_>
+          6 3 3 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 16 15 3 -1.</_>
+        <_>
+          9 17 5 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 4 3 -1.</_>
+        <_>
+          8 0 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 16 6 3 -1.</_>
+        <_>
+          6 17 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 6 13 -1.</_>
+        <_>
+          9 0 2 13 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 2 6 15 -1.</_>
+        <_>
+          9 2 2 15 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 2 -1.</_>
+        <_>
+          9 3 2 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 7 6 6 -1.</_>
+        <_>
+          9 9 2 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 4 6 -1.</_>
+        <_>
+          6 2 4 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 1 6 14 -1.</_>
+        <_>
+          9 1 3 7 2.</_>
+        <_>
+          12 8 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 3 9 15 -1.</_>
+        <_>
+          10 8 9 5 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 6 4 2 -1.</_>
+        <_>
+          12 6 2 1 2.</_>
+        <_>
+          14 7 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 10 8 6 -1.</_>
+        <_>
+          14 10 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 1 6 8 -1.</_>
+        <_>
+          12 3 6 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 4 1 -1.</_>
+        <_>
+          15 3 2 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 6 3 -1.</_>
+        <_>
+          14 3 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 3 2 8 -1.</_>
+        <_>
+          16 7 2 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 18 4 2 -1.</_>
+        <_>
+          18 18 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 0 1 20 -1.</_>
+        <_>
+          18 5 1 10 2.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test/cascade_my.xml

@@ -0,0 +1,39 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>1</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>1</maxWeakCount>
+      <stageThreshold>1.</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 0 1.1519325524568558e-01</internalNodes>
+          <leafValues>
+            -1. 1.</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          16 2 3 12 -1.</_>
+        <_>
+          12 6 3 4 3.</_></rects>
+      <tilted>1</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test/cascade_working_example.xml

@@ -0,0 +1,887 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-001</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-001</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-001</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>15</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-1.1904125660657883e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 27 3.4366466104984283e-002</internalNodes>
+          <leafValues>
+            -9.5959597826004028e-001 9.1111111640930176e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 17 3.5351995378732681e-002</internalNodes>
+          <leafValues>
+            -9.8020136356353760e-001 8.4055471420288086e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-1.6065055131912231e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 5 2.9048809409141541e-001</internalNodes>
+          <leafValues>
+            -9.4708997011184692e-001 7.1717172861099243e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 50 5.0262402743101120e-002</internalNodes>
+          <leafValues>
+            -7.7234727144241333e-001 7.8643941879272461e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.6334284543991089e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 51 5.3355745971202850e-002</internalNodes>
+          <leafValues>
+            -8.4158414602279663e-001 7.2093021869659424e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 1.9017890095710754e-002</internalNodes>
+          <leafValues>
+            -7.9365950822830200e-001 5.7417571544647217e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 8.4164272993803024e-003</internalNodes>
+          <leafValues>
+            -6.9593441486358643e-001 6.7576801776885986e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.0980907678604126e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 49 1.3862924277782440e-001</internalNodes>
+          <leafValues>
+            -7.8835976123809814e-001 4.1414141654968262e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 1.2018929421901703e-001</internalNodes>
+          <leafValues>
+            -8.2995903491973877e-001 5.1739817857742310e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 6.9296143949031830e-002</internalNodes>
+          <leafValues>
+            -7.7216577529907227e-001 5.2250796556472778e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 55 -6.9693401455879211e-003</internalNodes>
+          <leafValues>
+            6.8117576837539673e-001 -5.3906446695327759e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 23 -4.6523470431566238e-002</internalNodes>
+          <leafValues>
+            5.3678452968597412e-001 -7.2046381235122681e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.5287377834320068e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 30 5.9669867157936096e-002</internalNodes>
+          <leafValues>
+            -7.4489796161651611e-001 4.1304346919059753e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 1.3445684686303139e-002</internalNodes>
+          <leafValues>
+            -7.7788120508193970e-001 4.6229514479637146e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 45 -1.7986372113227844e-002</internalNodes>
+          <leafValues>
+            3.7505811452865601e-001 -8.3357995748519897e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 34 -1.1376420035958290e-002</internalNodes>
+          <leafValues>
+            4.6328634023666382e-001 -7.6309412717819214e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.4342429637908936e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 -5.8313719928264618e-003</internalNodes>
+          <leafValues>
+            3.4653463959693909e-001 -7.6470589637756348e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 3.2979757525026798e-003</internalNodes>
+          <leafValues>
+            -7.3521333932876587e-001 4.0015175938606262e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 2.8315588133409619e-004</internalNodes>
+          <leafValues>
+            -7.7022463083267212e-001 3.5349735617637634e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 42 -4.9816002137959003e-004</internalNodes>
+          <leafValues>
+            4.2861956357955933e-001 -7.0824295282363892e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.4555394649505615e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 4 5.7939004898071289e-001</internalNodes>
+          <leafValues>
+            -6.6183573007583618e-001 3.5802468657493591e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 -1.6687558963894844e-002</internalNodes>
+          <leafValues>
+            5.4647672176361084e-001 -5.3975820541381836e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 60 2.1265654140734114e-005</internalNodes>
+          <leafValues>
+            -6.2752234935760498e-001 3.9351144433021545e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 46 6.6983029246330261e-002</internalNodes>
+          <leafValues>
+            -9.2253303527832031e-001 2.4533702433109283e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-8.6999106407165527e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 22 3.2872073352336884e-002</internalNodes>
+          <leafValues>
+            -8.2278478145599365e-001 1.6923077404499054e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 56 1.1720009148120880e-001</internalNodes>
+          <leafValues>
+            -5.8168739080429077e-001 4.5801275968551636e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 6.9866264238953590e-003</internalNodes>
+          <leafValues>
+            -4.9278238415718079e-001 5.7913672924041748e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 -2.9733779374510050e-003</internalNodes>
+          <leafValues>
+            4.1448754072189331e-001 -6.2596440315246582e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 43 -4.4006314128637314e-003</internalNodes>
+          <leafValues>
+            7.4588859081268311e-001 -3.7923958897590637e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.2486633062362671e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 3 2.1714147180318832e-002</internalNodes>
+          <leafValues>
+            -8.0263155698776245e-001 1.0294117778539658e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 53 7.8238844871520996e-003</internalNodes>
+          <leafValues>
+            -5.0123983621597290e-001 5.8820140361785889e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.6540891267359257e-003</internalNodes>
+          <leafValues>
+            -4.9355110526084900e-001 5.1366353034973145e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 59 -1.1731262784451246e-003</internalNodes>
+          <leafValues>
+            -8.4023118019104004e-001 2.9721990227699280e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.0818475484848022e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 31 5.2707802504301071e-002</internalNodes>
+          <leafValues>
+            -6.8527919054031372e-001 2.9670330882072449e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 8 6.7518748342990875e-002</internalNodes>
+          <leafValues>
+            -7.6223957538604736e-001 3.2997161149978638e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 48 -1.2102196924388409e-003</internalNodes>
+          <leafValues>
+            5.8841788768768311e-001 -4.3890732526779175e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 11 2.1901189029449597e-005</internalNodes>
+          <leafValues>
+            -7.3106634616851807e-001 3.7173879146575928e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>6</maxWeakCount>
+      <stageThreshold>-1.0043972730636597e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 19 1.8333575129508972e-001</internalNodes>
+          <leafValues>
+            -6.5581393241882324e-001 4.5205479860305786e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 40 -4.2812071740627289e-002</internalNodes>
+          <leafValues>
+            4.3029156327247620e-001 -5.0881063938140869e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 57 -1.0015382431447506e-002</internalNodes>
+          <leafValues>
+            3.2117792963981628e-001 -6.6418427228927612e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 5.0185494124889374e-002</internalNodes>
+          <leafValues>
+            -5.9623473882675171e-001 3.6050540208816528e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 36 -2.8086153324693441e-003</internalNodes>
+          <leafValues>
+            -8.8960582017898560e-001 2.5818291306495667e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 64 -1.2656298931688070e-003</internalNodes>
+          <leafValues>
+            -8.5023450851440430e-001 2.4564331769943237e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>7</maxWeakCount>
+      <stageThreshold>-8.6170506477355957e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 54 9.7151473164558411e-002</internalNodes>
+          <leafValues>
+            -5.8441555500030518e-001 4.7368422150611877e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 41 -2.7522351592779160e-002</internalNodes>
+          <leafValues>
+            4.1773623228073120e-001 -5.2829349040985107e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 47 -5.0151135772466660e-002</internalNodes>
+          <leafValues>
+            4.1643708944320679e-001 -5.1419234275817871e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 13 -1.1980412527918816e-003</internalNodes>
+          <leafValues>
+            2.3611299693584442e-001 -8.2664483785629272e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 3.4218670334666967e-003</internalNodes>
+          <leafValues>
+            -7.1486043930053711e-001 2.9136228561401367e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 4.1605886071920395e-003</internalNodes>
+          <leafValues>
+            -3.7625908851623535e-001 6.1018615961074829e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 44 5.8592204004526138e-003</internalNodes>
+          <leafValues>
+            -2.5573691725730896e-001 8.4279149770736694e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 12 -->
+    <_>
+      <maxWeakCount>6</maxWeakCount>
+      <stageThreshold>-1.0506447553634644e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 33 3.0356062576174736e-002</internalNodes>
+          <leafValues>
+            -7.0454543828964233e-001 1.4285714924335480e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 61 -1.1418197304010391e-002</internalNodes>
+          <leafValues>
+            5.7870584726333618e-001 -3.9473026990890503e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 62 8.5939792916178703e-003</internalNodes>
+          <leafValues>
+            -7.2573381662368774e-001 2.9877531528472900e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 35 1.3435125350952148e-002</internalNodes>
+          <leafValues>
+            -5.8302259445190430e-001 3.9270570874214172e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 63 -1.2715969933196902e-003</internalNodes>
+          <leafValues>
+            -8.4091544151306152e-001 2.8896194696426392e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 -4.0338272228837013e-003</internalNodes>
+          <leafValues>
+            -8.5489493608474731e-001 2.2102287411689758e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 13 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-5.9828740358352661e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 26 -1.6393268480896950e-002</internalNodes>
+          <leafValues>
+            6.7567569017410278e-001 -5.2988046407699585e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 14 3.6920449929311872e-004</internalNodes>
+          <leafValues>
+            2.9523831605911255e-001 -7.1965837478637695e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 58 8.9285410940647125e-003</internalNodes>
+          <leafValues>
+            -5.7257694005966187e-001 3.8740223646163940e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 2.5883363559842110e-003</internalNodes>
+          <leafValues>
+            2.6384916901588440e-001 -9.8422628641128540e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 14 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-7.3297047615051270e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 24 -2.5055244565010071e-002</internalNodes>
+          <leafValues>
+            6.0869562625885010e-001 -5.6198346614837646e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 52 1.7512582708150148e-003</internalNodes>
+          <leafValues>
+            -7.1301835775375366e-001 2.6307231187820435e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 39 4.4407839886844158e-003</internalNodes>
+          <leafValues>
+            -3.7482297420501709e-001 5.8060395717620850e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 3.7488103844225407e-003</internalNodes>
+          <leafValues>
+            3.4034672379493713e-001 -6.6739976406097412e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 38 -5.2913911640644073e-003</internalNodes>
+          <leafValues>
+            6.2683594226837158e-001 -3.4726351499557495e-001</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 4 1 -1.</_>
+        <_>
+          2 0 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 6 3 -1.</_>
+        <_>
+          3 0 3 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 18 -1.</_>
+        <_>
+          0 6 20 6 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 1 20 18 -1.</_>
+        <_>
+          0 7 20 6 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 2 5 3 -1.</_>
+        <_>
+          0 3 5 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 6 15 -1.</_>
+        <_>
+          2 8 2 5 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 11 8 -1.</_>
+        <_>
+          0 7 11 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 2 15 -1.</_>
+        <_>
+          1 5 1 15 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 8 1 4 -1.</_>
+        <_>
+          0 9 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 8 4 4 -1.</_>
+        <_>
+          0 9 4 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 11 2 9 -1.</_>
+        <_>
+          1 11 1 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 11 5 4 -1.</_>
+        <_>
+          0 13 5 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 2 6 -1.</_>
+        <_>
+          0 17 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 18 10 2 -1.</_>
+        <_>
+          0 18 5 1 2.</_>
+        <_>
+          5 19 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 11 1 6 -1.</_>
+        <_>
+          1 13 1 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 0 10 7 -1.</_>
+        <_>
+          7 0 5 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 2 4 3 -1.</_>
+        <_>
+          2 3 4 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 5 16 15 -1.</_>
+        <_>
+          10 5 8 15 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 1 8 5 -1.</_>
+        <_>
+          7 1 4 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 9 4 9 -1.</_>
+        <_>
+          6 9 2 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 1 6 5 -1.</_>
+        <_>
+          8 1 3 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 2 8 2 -1.</_>
+        <_>
+          5 2 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 5 6 3 -1.</_>
+        <_>
+          7 5 2 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 8 4 1 -1.</_>
+        <_>
+          5 8 2 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 13 10 2 -1.</_>
+        <_>
+          5 14 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 8 12 -1.</_>
+        <_>
+          8 0 4 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 15 5 3 -1.</_>
+        <_>
+          6 16 5 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 12 16 -1.</_>
+        <_>
+          7 0 6 8 2.</_>
+        <_>
+          13 8 6 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 6 11 -1.</_>
+        <_>
+          9 1 2 11 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 2 6 7 -1.</_>
+        <_>
+          9 2 2 7 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 3 -1.</_>
+        <_>
+          9 3 2 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 8 4 -1.</_>
+        <_>
+          9 3 4 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 12 1 -1.</_>
+        <_>
+          13 3 6 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 9 6 3 -1.</_>
+        <_>
+          9 10 2 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 5 3 4 -1.</_>
+        <_>
+          8 7 3 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 6 5 2 -1.</_>
+        <_>
+          8 7 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 17 10 2 -1.</_>
+        <_>
+          8 17 5 1 2.</_>
+        <_>
+          13 18 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 18 5 2 -1.</_>
+        <_>
+          8 19 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 0 8 12 -1.</_>
+        <_>
+          11 0 4 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 4 8 8 -1.</_>
+        <_>
+          11 4 4 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 10 8 1 -1.</_>
+        <_>
+          11 10 4 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 16 2 3 -1.</_>
+        <_>
+          9 17 2 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 13 2 4 -1.</_>
+        <_>
+          10 14 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 1 7 6 -1.</_>
+        <_>
+          11 3 7 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 1 9 12 -1.</_>
+        <_>
+          11 7 9 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 1 6 6 -1.</_>
+        <_>
+          15 3 2 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 2 2 2 -1.</_>
+        <_>
+          13 2 1 1 2.</_>
+        <_>
+          14 3 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 6 12 -1.</_>
+        <_>
+          16 7 2 4 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 3 8 -1.</_>
+        <_>
+          12 5 3 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 4 8 -1.</_>
+        <_>
+          14 7 4 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 7 6 4 -1.</_>
+        <_>
+          14 8 6 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 0 3 3 -1.</_>
+        <_>
+          16 1 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 0 3 9 -1.</_>
+        <_>
+          12 3 3 3 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 2 3 3 -1.</_>
+        <_>
+          16 3 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 5 5 10 -1.</_>
+        <_>
+          15 5 5 5 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 0 1 9 -1.</_>
+        <_>
+          16 3 1 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 5 4 4 -1.</_>
+        <_>
+          15 6 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 9 3 3 -1.</_>
+        <_>
+          17 10 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 12 4 2 -1.</_>
+        <_>
+          17 12 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 15 4 5 -1.</_>
+        <_>
+          18 15 2 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 0 1 10 -1.</_>
+        <_>
+          18 5 1 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 9 2 4 -1.</_>
+        <_>
+          18 9 1 2 2.</_>
+        <_>
+          19 11 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 15 1 3 -1.</_>
+        <_>
+          19 16 1 1 3.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test/test.py

@@ -0,0 +1,41 @@
+import cv2
+import os,sys
+
+# 获取 XML 文件，加载人脸检测器
+faceCascade = cv2.CascadeClassifier("cascade.xml")
+
+
+# 读取待检测的图像
+image_set = []
+for i in range(1,12+1):
+    file_name = "iut/{}.jpg".format(i)
+    image_set.append([cv2.imread(file_name), file_name])
+
+for i in range(len(image_set)):
+    image = image_set[i][0]
+    file_name = image_set[i][1]
+    re_file_name = file_name.replace(".jpg","_re.jpg").replace('iut/', 'iut_re/')
+    # 色彩转换，转换为灰度图像
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+    # 调用函数 detectMultiScale
+    faces = faceCascade.detectMultiScale(gray, scaleFactor=1.15, minNeighbors=5, minSize=(5, 5))
+
+    # print(faces)
+    # 打印输出的测试结果
+    # print("found {0} face in {1}".format(len(faces), os.path.basename(file_name)))
+    print((re_file_name, len(faces)))
+
+    # 逐个标注人脸
+    for x, y, w, h in faces:
+        cv2.rectangle(image, (x, y), (x + w, y + w), (0, 255, 0), 2)  # 矩形标注
+        # cv2.circle(image,(int((x+x+w)/2),int((y+y+h)/2)),int(w/2),(0,255,0),2)
+
+    # 显示结果
+    cv2.imshow("dect", image)
+    # 保存检测结果
+    cv2.imwrite(re_file_name, image)
+    # cv2.waitKey(0)
+    cv2.destroyAllWindows()
+
+    

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test/test.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+set -ex
+
+npx nodemon --ext xml --exec "python ./test.py"

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test_original/cascade.xml

@@ -0,0 +1,544 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>12</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-2.0792216528207064e-03</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 23 3.5195697098970413e-02</internalNodes>
+          <leafValues>
+            -9.7000002861022949e-01 9.5833331346511841e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 4.9420498311519623e-02</internalNodes>
+          <leafValues>
+            -9.3253821134567261e-01 9.6792078018188477e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2283716201782227e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 2.1136376261711121e-01</internalNodes>
+          <leafValues>
+            -8.8292682170867920e-01 7.6744186878204346e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 -3.6786209791898727e-02</internalNodes>
+          <leafValues>
+            6.4631646871566772e-01 -8.5865759849548340e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 8.2553006708621979e-02</internalNodes>
+          <leafValues>
+            -9.6414572000503540e-01 5.1321285963058472e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.2522403001785278e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 34 -7.0488560013473034e-03</internalNodes>
+          <leafValues>
+            4.6428570151329041e-01 -9.0625000000000000e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 2.0252991467714310e-02</internalNodes>
+          <leafValues>
+            -9.2222303152084351e-01 3.8102594017982483e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2258527278900146e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 35 2.7621425688266754e-02</internalNodes>
+          <leafValues>
+            -9.3296086788177490e-01 2.7536231279373169e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 2.4644609540700912e-02</internalNodes>
+          <leafValues>
+            -7.8042775392532349e-01 5.6246817111968994e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 4.4026337563991547e-02</internalNodes>
+          <leafValues>
+            -7.2078734636306763e-01 5.9029269218444824e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.1094360351562500e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 13 5.6299664080142975e-02</internalNodes>
+          <leafValues>
+            -8.5567009449005127e-01 3.3333334326744080e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 2.0412717014551163e-02</internalNodes>
+          <leafValues>
+            -6.9705963134765625e-01 6.2128168344497681e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 3.3632911741733551e-02</internalNodes>
+          <leafValues>
+            -7.4570971727371216e-01 6.2287092208862305e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-1.0068651437759399e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 14 2.7963671088218689e-01</internalNodes>
+          <leafValues>
+            -8.6885243654251099e-01 1.6923077404499054e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 1.2323195114731789e-02</internalNodes>
+          <leafValues>
+            -7.9252362251281738e-01 3.5135197639465332e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 1.1619093269109726e-01</internalNodes>
+          <leafValues>
+            -8.5458588600158691e-01 4.3786722421646118e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 1.1368356645107269e-02</internalNodes>
+          <leafValues>
+            -8.9688044786453247e-01 3.6522126197814941e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.4377774000167847e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 17 2.8343785554170609e-02</internalNodes>
+          <leafValues>
+            -7.5813955068588257e-01 4.5454546809196472e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 -6.7780455574393272e-03</internalNodes>
+          <leafValues>
+            6.8800747394561768e-01 -5.7961523532867432e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 -9.6869543194770813e-03</internalNodes>
+          <leafValues>
+            5.2493661642074585e-01 -8.1870794296264648e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.8824944496154785e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 8 2.2776421904563904e-01</internalNodes>
+          <leafValues>
+            -7.8431373834609985e-01 2.7272728085517883e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 4 -1.3495892286300659e-01</internalNodes>
+          <leafValues>
+            3.2428205013275146e-01 -8.6097669601440430e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.8578220605850220e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 31 3.1056167557835579e-02</internalNodes>
+          <leafValues>
+            -7.7464789152145386e-01 4.8571428656578064e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.3904092609882355e-02</internalNodes>
+          <leafValues>
+            -7.8261238336563110e-01 4.7452750802040100e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 24 5.9338808059692383e-02</internalNodes>
+          <leafValues>
+            -6.1228525638580322e-01 5.7147806882858276e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2791478633880615e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 11 -1.5193784609436989e-02</internalNodes>
+          <leafValues>
+            -6.0240965336561203e-02 -8.6666667461395264e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 3 1.2929022312164307e-01</internalNodes>
+          <leafValues>
+            -7.7955096960067749e-01 2.7296727895736694e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 30 2.4830256006680429e-04</internalNodes>
+          <leafValues>
+            -8.2253754138946533e-01 3.6706984043121338e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-9.7741711139678955e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 36 -7.1106562390923500e-03</internalNodes>
+          <leafValues>
+            7.4074074625968933e-02 -7.8350514173507690e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 1.0002901777625084e-02</internalNodes>
+          <leafValues>
+            -9.6380352973937988e-01 1.2861841917037964e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 -1.1527233757078648e-02</internalNodes>
+          <leafValues>
+            3.1283980607986450e-01 -7.8981834650039673e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 7.7132084406912327e-03</internalNodes>
+          <leafValues>
+            -9.2314887046813965e-01 3.5634875297546387e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 -2.8069035615772009e-03</internalNodes>
+          <leafValues>
+            3.7375229597091675e-01 -7.4664002656936646e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.3949387073516846e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 19 4.9728322774171829e-03</internalNodes>
+          <leafValues>
+            -7.8894472122192383e-01 1.8367347121238708e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 8.1018730998039246e-03</internalNodes>
+          <leafValues>
+            -7.9892826080322266e-01 2.1818427741527557e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 9.7033903002738953e-03</internalNodes>
+          <leafValues>
+            -5.7855868339538574e-01 4.4443655014038086e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 -6.7393705248832703e-02</internalNodes>
+          <leafValues>
+            6.7329019308090210e-01 -4.4816955924034119e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 3.2395221292972565e-02</internalNodes>
+          <leafValues>
+            -8.7441539764404297e-01 4.0108311176300049e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 12 6 -1.</_>
+        <_>
+          6 0 6 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 7 20 -1.</_>
+        <_>
+          0 5 7 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 9 -1.</_>
+        <_>
+          0 3 20 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 2 16 -1.</_>
+        <_>
+          1 4 1 16 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 20 12 -1.</_>
+        <_>
+          0 7 20 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 6 9 -1.</_>
+        <_>
+          0 8 6 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 6 20 12 -1.</_>
+        <_>
+          10 6 10 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 12 3 8 -1.</_>
+        <_>
+          0 16 3 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 8 6 -1.</_>
+        <_>
+          2 14 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 15 3 -1.</_>
+        <_>
+          1 3 15 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 16 3 -1.</_>
+        <_>
+          1 3 16 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 5 6 -1.</_>
+        <_>
+          1 6 5 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 18 16 -1.</_>
+        <_>
+          1 7 18 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 3 16 1 -1.</_>
+        <_>
+          6 3 8 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 5 6 2 -1.</_>
+        <_>
+          4 7 2 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 9 6 9 -1.</_>
+        <_>
+          4 9 2 9 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 0 1 12 -1.</_>
+        <_>
+          3 6 1 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 2 6 2 -1.</_>
+        <_>
+          3 2 3 1 2.</_>
+        <_>
+          6 3 3 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 16 15 3 -1.</_>
+        <_>
+          9 17 5 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 4 3 -1.</_>
+        <_>
+          8 0 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 16 6 3 -1.</_>
+        <_>
+          6 17 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 6 13 -1.</_>
+        <_>
+          9 0 2 13 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 2 6 15 -1.</_>
+        <_>
+          9 2 2 15 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 2 -1.</_>
+        <_>
+          9 3 2 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 7 6 6 -1.</_>
+        <_>
+          9 9 2 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 4 6 -1.</_>
+        <_>
+          6 2 4 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 1 6 14 -1.</_>
+        <_>
+          9 1 3 7 2.</_>
+        <_>
+          12 8 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 3 9 15 -1.</_>
+        <_>
+          10 8 9 5 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 6 4 2 -1.</_>
+        <_>
+          12 6 2 1 2.</_>
+        <_>
+          14 7 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          12 10 8 6 -1.</_>
+        <_>
+          14 10 4 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 1 6 8 -1.</_>
+        <_>
+          12 3 6 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 4 1 -1.</_>
+        <_>
+          15 3 2 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 6 3 -1.</_>
+        <_>
+          14 3 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 3 2 8 -1.</_>
+        <_>
+          16 7 2 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 18 4 2 -1.</_>
+        <_>
+          18 18 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 0 1 20 -1.</_>
+        <_>
+          18 5 1 10 2.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test_original/cascade_my.xml

@@ -0,0 +1,39 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>1</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>1</maxWeakCount>
+      <stageThreshold>1.</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 0 1.1519325524568558e-01</internalNodes>
+          <leafValues>
+            -1. 1.</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          16 2 3 12 -1.</_>
+        <_>
+          12 6 3 4 3.</_></rects>
+      <tilted>1</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test_original/cascade_working_example.xml

@@ -0,0 +1,887 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-001</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-001</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-001</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>15</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-1.1904125660657883e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 27 3.4366466104984283e-002</internalNodes>
+          <leafValues>
+            -9.5959597826004028e-001 9.1111111640930176e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 17 3.5351995378732681e-002</internalNodes>
+          <leafValues>
+            -9.8020136356353760e-001 8.4055471420288086e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-1.6065055131912231e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 5 2.9048809409141541e-001</internalNodes>
+          <leafValues>
+            -9.4708997011184692e-001 7.1717172861099243e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 50 5.0262402743101120e-002</internalNodes>
+          <leafValues>
+            -7.7234727144241333e-001 7.8643941879272461e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.6334284543991089e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 51 5.3355745971202850e-002</internalNodes>
+          <leafValues>
+            -8.4158414602279663e-001 7.2093021869659424e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 1.9017890095710754e-002</internalNodes>
+          <leafValues>
+            -7.9365950822830200e-001 5.7417571544647217e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 8.4164272993803024e-003</internalNodes>
+          <leafValues>
+            -6.9593441486358643e-001 6.7576801776885986e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.0980907678604126e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 49 1.3862924277782440e-001</internalNodes>
+          <leafValues>
+            -7.8835976123809814e-001 4.1414141654968262e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 1.2018929421901703e-001</internalNodes>
+          <leafValues>
+            -8.2995903491973877e-001 5.1739817857742310e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 6.9296143949031830e-002</internalNodes>
+          <leafValues>
+            -7.7216577529907227e-001 5.2250796556472778e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 55 -6.9693401455879211e-003</internalNodes>
+          <leafValues>
+            6.8117576837539673e-001 -5.3906446695327759e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 23 -4.6523470431566238e-002</internalNodes>
+          <leafValues>
+            5.3678452968597412e-001 -7.2046381235122681e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.5287377834320068e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 30 5.9669867157936096e-002</internalNodes>
+          <leafValues>
+            -7.4489796161651611e-001 4.1304346919059753e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 1.3445684686303139e-002</internalNodes>
+          <leafValues>
+            -7.7788120508193970e-001 4.6229514479637146e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 45 -1.7986372113227844e-002</internalNodes>
+          <leafValues>
+            3.7505811452865601e-001 -8.3357995748519897e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 34 -1.1376420035958290e-002</internalNodes>
+          <leafValues>
+            4.6328634023666382e-001 -7.6309412717819214e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.4342429637908936e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 -5.8313719928264618e-003</internalNodes>
+          <leafValues>
+            3.4653463959693909e-001 -7.6470589637756348e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 3.2979757525026798e-003</internalNodes>
+          <leafValues>
+            -7.3521333932876587e-001 4.0015175938606262e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 2.8315588133409619e-004</internalNodes>
+          <leafValues>
+            -7.7022463083267212e-001 3.5349735617637634e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 42 -4.9816002137959003e-004</internalNodes>
+          <leafValues>
+            4.2861956357955933e-001 -7.0824295282363892e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.4555394649505615e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 4 5.7939004898071289e-001</internalNodes>
+          <leafValues>
+            -6.6183573007583618e-001 3.5802468657493591e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 21 -1.6687558963894844e-002</internalNodes>
+          <leafValues>
+            5.4647672176361084e-001 -5.3975820541381836e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 60 2.1265654140734114e-005</internalNodes>
+          <leafValues>
+            -6.2752234935760498e-001 3.9351144433021545e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 46 6.6983029246330261e-002</internalNodes>
+          <leafValues>
+            -9.2253303527832031e-001 2.4533702433109283e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-8.6999106407165527e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 22 3.2872073352336884e-002</internalNodes>
+          <leafValues>
+            -8.2278478145599365e-001 1.6923077404499054e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 56 1.1720009148120880e-001</internalNodes>
+          <leafValues>
+            -5.8168739080429077e-001 4.5801275968551636e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 6.9866264238953590e-003</internalNodes>
+          <leafValues>
+            -4.9278238415718079e-001 5.7913672924041748e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 -2.9733779374510050e-003</internalNodes>
+          <leafValues>
+            4.1448754072189331e-001 -6.2596440315246582e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 43 -4.4006314128637314e-003</internalNodes>
+          <leafValues>
+            7.4588859081268311e-001 -3.7923958897590637e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.2486633062362671e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 3 2.1714147180318832e-002</internalNodes>
+          <leafValues>
+            -8.0263155698776245e-001 1.0294117778539658e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 53 7.8238844871520996e-003</internalNodes>
+          <leafValues>
+            -5.0123983621597290e-001 5.8820140361785889e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.6540891267359257e-003</internalNodes>
+          <leafValues>
+            -4.9355110526084900e-001 5.1366353034973145e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 59 -1.1731262784451246e-003</internalNodes>
+          <leafValues>
+            -8.4023118019104004e-001 2.9721990227699280e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.0818475484848022e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 31 5.2707802504301071e-002</internalNodes>
+          <leafValues>
+            -6.8527919054031372e-001 2.9670330882072449e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 8 6.7518748342990875e-002</internalNodes>
+          <leafValues>
+            -7.6223957538604736e-001 3.2997161149978638e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 48 -1.2102196924388409e-003</internalNodes>
+          <leafValues>
+            5.8841788768768311e-001 -4.3890732526779175e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 11 2.1901189029449597e-005</internalNodes>
+          <leafValues>
+            -7.3106634616851807e-001 3.7173879146575928e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>6</maxWeakCount>
+      <stageThreshold>-1.0043972730636597e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 19 1.8333575129508972e-001</internalNodes>
+          <leafValues>
+            -6.5581393241882324e-001 4.5205479860305786e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 40 -4.2812071740627289e-002</internalNodes>
+          <leafValues>
+            4.3029156327247620e-001 -5.0881063938140869e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 57 -1.0015382431447506e-002</internalNodes>
+          <leafValues>
+            3.2117792963981628e-001 -6.6418427228927612e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 5.0185494124889374e-002</internalNodes>
+          <leafValues>
+            -5.9623473882675171e-001 3.6050540208816528e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 36 -2.8086153324693441e-003</internalNodes>
+          <leafValues>
+            -8.8960582017898560e-001 2.5818291306495667e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 64 -1.2656298931688070e-003</internalNodes>
+          <leafValues>
+            -8.5023450851440430e-001 2.4564331769943237e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>7</maxWeakCount>
+      <stageThreshold>-8.6170506477355957e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 54 9.7151473164558411e-002</internalNodes>
+          <leafValues>
+            -5.8441555500030518e-001 4.7368422150611877e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 41 -2.7522351592779160e-002</internalNodes>
+          <leafValues>
+            4.1773623228073120e-001 -5.2829349040985107e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 47 -5.0151135772466660e-002</internalNodes>
+          <leafValues>
+            4.1643708944320679e-001 -5.1419234275817871e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 13 -1.1980412527918816e-003</internalNodes>
+          <leafValues>
+            2.3611299693584442e-001 -8.2664483785629272e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 3.4218670334666967e-003</internalNodes>
+          <leafValues>
+            -7.1486043930053711e-001 2.9136228561401367e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 4.1605886071920395e-003</internalNodes>
+          <leafValues>
+            -3.7625908851623535e-001 6.1018615961074829e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 44 5.8592204004526138e-003</internalNodes>
+          <leafValues>
+            -2.5573691725730896e-001 8.4279149770736694e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 12 -->
+    <_>
+      <maxWeakCount>6</maxWeakCount>
+      <stageThreshold>-1.0506447553634644e+000</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 33 3.0356062576174736e-002</internalNodes>
+          <leafValues>
+            -7.0454543828964233e-001 1.4285714924335480e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 61 -1.1418197304010391e-002</internalNodes>
+          <leafValues>
+            5.7870584726333618e-001 -3.9473026990890503e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 62 8.5939792916178703e-003</internalNodes>
+          <leafValues>
+            -7.2573381662368774e-001 2.9877531528472900e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 35 1.3435125350952148e-002</internalNodes>
+          <leafValues>
+            -5.8302259445190430e-001 3.9270570874214172e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 63 -1.2715969933196902e-003</internalNodes>
+          <leafValues>
+            -8.4091544151306152e-001 2.8896194696426392e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 -4.0338272228837013e-003</internalNodes>
+          <leafValues>
+            -8.5489493608474731e-001 2.2102287411689758e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 13 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-5.9828740358352661e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 26 -1.6393268480896950e-002</internalNodes>
+          <leafValues>
+            6.7567569017410278e-001 -5.2988046407699585e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 14 3.6920449929311872e-004</internalNodes>
+          <leafValues>
+            2.9523831605911255e-001 -7.1965837478637695e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 58 8.9285410940647125e-003</internalNodes>
+          <leafValues>
+            -5.7257694005966187e-001 3.8740223646163940e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 10 2.5883363559842110e-003</internalNodes>
+          <leafValues>
+            2.6384916901588440e-001 -9.8422628641128540e-001</leafValues></_></weakClassifiers></_>
+    <!-- stage 14 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-7.3297047615051270e-001</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 24 -2.5055244565010071e-002</internalNodes>
+          <leafValues>
+            6.0869562625885010e-001 -5.6198346614837646e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 52 1.7512582708150148e-003</internalNodes>
+          <leafValues>
+            -7.1301835775375366e-001 2.6307231187820435e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 39 4.4407839886844158e-003</internalNodes>
+          <leafValues>
+            -3.7482297420501709e-001 5.8060395717620850e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 3.7488103844225407e-003</internalNodes>
+          <leafValues>
+            3.4034672379493713e-001 -6.6739976406097412e-001</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 38 -5.2913911640644073e-003</internalNodes>
+          <leafValues>
+            6.2683594226837158e-001 -3.4726351499557495e-001</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 4 1 -1.</_>
+        <_>
+          2 0 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 6 3 -1.</_>
+        <_>
+          3 0 3 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 18 -1.</_>
+        <_>
+          0 6 20 6 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 1 20 18 -1.</_>
+        <_>
+          0 7 20 6 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 2 5 3 -1.</_>
+        <_>
+          0 3 5 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 6 15 -1.</_>
+        <_>
+          2 8 2 5 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 11 8 -1.</_>
+        <_>
+          0 7 11 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 5 2 15 -1.</_>
+        <_>
+          1 5 1 15 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 8 1 4 -1.</_>
+        <_>
+          0 9 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 8 4 4 -1.</_>
+        <_>
+          0 9 4 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 11 2 9 -1.</_>
+        <_>
+          1 11 1 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 11 5 4 -1.</_>
+        <_>
+          0 13 5 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 2 6 -1.</_>
+        <_>
+          0 17 2 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 18 10 2 -1.</_>
+        <_>
+          0 18 5 1 2.</_>
+        <_>
+          5 19 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 11 1 6 -1.</_>
+        <_>
+          1 13 1 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 0 10 7 -1.</_>
+        <_>
+          7 0 5 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 2 4 3 -1.</_>
+        <_>
+          2 3 4 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 5 16 15 -1.</_>
+        <_>
+          10 5 8 15 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 1 8 5 -1.</_>
+        <_>
+          7 1 4 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 9 4 9 -1.</_>
+        <_>
+          6 9 2 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 1 6 5 -1.</_>
+        <_>
+          8 1 3 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 2 8 2 -1.</_>
+        <_>
+          5 2 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 5 6 3 -1.</_>
+        <_>
+          7 5 2 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 8 4 1 -1.</_>
+        <_>
+          5 8 2 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 13 10 2 -1.</_>
+        <_>
+          5 14 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 8 12 -1.</_>
+        <_>
+          8 0 4 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 15 5 3 -1.</_>
+        <_>
+          6 16 5 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 0 12 16 -1.</_>
+        <_>
+          7 0 6 8 2.</_>
+        <_>
+          13 8 6 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 6 11 -1.</_>
+        <_>
+          9 1 2 11 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 2 6 7 -1.</_>
+        <_>
+          9 2 2 7 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 3 -1.</_>
+        <_>
+          9 3 2 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 8 4 -1.</_>
+        <_>
+          9 3 4 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 12 1 -1.</_>
+        <_>
+          13 3 6 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 9 6 3 -1.</_>
+        <_>
+          9 10 2 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 5 3 4 -1.</_>
+        <_>
+          8 7 3 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 6 5 2 -1.</_>
+        <_>
+          8 7 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 17 10 2 -1.</_>
+        <_>
+          8 17 5 1 2.</_>
+        <_>
+          13 18 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 18 5 2 -1.</_>
+        <_>
+          8 19 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 0 8 12 -1.</_>
+        <_>
+          11 0 4 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 4 8 8 -1.</_>
+        <_>
+          11 4 4 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 10 8 1 -1.</_>
+        <_>
+          11 10 4 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 16 2 3 -1.</_>
+        <_>
+          9 17 2 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 13 2 4 -1.</_>
+        <_>
+          10 14 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 1 7 6 -1.</_>
+        <_>
+          11 3 7 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 1 9 12 -1.</_>
+        <_>
+          11 7 9 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 1 6 6 -1.</_>
+        <_>
+          15 3 2 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 2 2 2 -1.</_>
+        <_>
+          13 2 1 1 2.</_>
+        <_>
+          14 3 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 6 12 -1.</_>
+        <_>
+          16 7 2 4 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 3 8 -1.</_>
+        <_>
+          12 5 3 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 4 8 -1.</_>
+        <_>
+          14 7 4 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 7 6 4 -1.</_>
+        <_>
+          14 8 6 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 0 3 3 -1.</_>
+        <_>
+          16 1 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 0 3 9 -1.</_>
+        <_>
+          12 3 3 3 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 2 3 3 -1.</_>
+        <_>
+          16 3 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 5 5 10 -1.</_>
+        <_>
+          15 5 5 5 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 0 1 9 -1.</_>
+        <_>
+          16 3 1 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 5 4 4 -1.</_>
+        <_>
+          15 6 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 9 3 3 -1.</_>
+        <_>
+          17 10 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 12 4 2 -1.</_>
+        <_>
+          17 12 2 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 15 4 5 -1.</_>
+        <_>
+          18 15 2 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 0 1 10 -1.</_>
+        <_>
+          18 5 1 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 9 2 4 -1.</_>
+        <_>
+          18 9 1 2 2.</_>
+        <_>
+          19 11 1 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 15 1 3 -1.</_>
+        <_>
+          19 16 1 1 3.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test_original/face_test.py

@@ -0,0 +1,29 @@
+import cv2
+
+# 读取待检测的图像
+image = cv2.imread("12.jpg")
+
+# 获取 XML 文件，加载人脸检测器
+faceCascade = cv2.CascadeClassifier("cascade.xml")
+
+# 色彩转换，转换为灰度图像
+gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+# 调用函数 detectMultiScale
+faces = faceCascade.detectMultiScale(gray, scaleFactor=1.15, minNeighbors=5, minSize=(5, 5))
+
+# print(faces)
+# 打印输出的测试结果
+print("发现{0}个人脸!".format(len(faces)))
+
+# 逐个标注人脸
+for x, y, w, h in faces:
+    cv2.rectangle(image, (x, y), (x + w, y + w), (0, 255, 0), 2)  # 矩形标注
+    # cv2.circle(image,(int((x+x+w)/2),int((y+y+h)/2)),int(w/2),(0,255,0),2)
+
+# 显示结果
+cv2.imshow("dect", image)
+# 保存检测结果
+cv2.imwrite("re.jpg", image)
+# cv2.waitKey(0)
+cv2.destroyAllWindows()

vinniesniper-54816/task1/_lab/007-train-beach-test2/test_case/face_test_original/test.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+
+set -ex
+
+npx nodemon --ext xml --exec "python ./face_test.py"

vinniesniper-54816/task1/_lab/007-train-beach-test2/train.sh

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+set -ex
+
+width_height=24
+file_num=100
+slice_num=200
+
+cd slice_image 
+    python slice_image.py $width_height $width_height $file_num $slice_num
+cd ..
+
+rm -rf posdata_400/*.jpg
+cp -r slice_image/output/*.jpg posdata_400
+echo "slice done"
+
+cd negdata_wo_beach
+    # python _ReName.py
+    python ./_GenTXT.py
+    python ./_copy.py
+    num_of_neg_file=$(find . -type f -name "*.jpg" | wc -l)
+cd ..
+
+wc -l neg.txt
+
+cd posdata_400
+    # python _ReName.py
+    python ./_GenTXT.py
+    python ./_copy.py
+    num_of_pos_file=$(find . -type f -name "*.jpg" | wc -l)
+cd ..
+
+echo "count pos file"
+echo $num_of_pos_file
+wc -l pos.txt
+read -p "Press [Enter] key to continue..." tmp
+
+
+python ./process_txt_files.py $width_height $width_height
+
+# ./step1.sh
+rm -rf pos.vec
+opencv_createsamples \
+    -info pos.txt \
+    -vec pos.vec  \
+    -num 200 \
+    -w $width_height -h $width_height
+
+# ./step2_t1.sh
+rm -rf xml_step2_t1/*.xml
+
+echo "clean done"
+
+opencv_traincascade \
+    -data xml_step2_t1 \
+    -vec pos.vec \
+    -bg neg.txt \
+    -numPos 200 \
+    -numNeg $num_of_neg_file \
+    -numStages 15 \
+    -numThreads 4 \
+    -maxFalseAlarmRate 0.5 \
+    -w $width_height -h $width_height \
+    -mode ALL
+
+
+cp xml_step2_t1/cascade.xml test_case/beach_test/cascade.xml
+cd test_case/beach_test
+    ./sanity_test.sh
+cd ..
+
+echo "done"
+exit 0

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/params.xml

@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<params>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>24</height>
+  <width>24</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams></params>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage0.xml

@@ -0,0 +1,52 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage0>
+  <maxWeakCount>9</maxWeakCount>
+  <stageThreshold>-1.9376053810119629e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 224740 1.1752764112316072e-04</internalNodes>
+      <leafValues>
+        -8.9389616250991821e-01 -4.8803827166557312e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 152582 -8.9311935880687088e-05</internalNodes>
+      <leafValues>
+        1.4782391488552094e-01 -6.0293614864349365e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 258916 2.8834943077526987e-04</internalNodes>
+      <leafValues>
+        -3.0809888243675232e-01 4.3221384286880493e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 87616 -9.5256080385297537e-05</internalNodes>
+      <leafValues>
+        3.6418572068214417e-01 -3.1319683790206909e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 32572 -1.4921249821782112e-03</internalNodes>
+      <leafValues>
+        3.9931476116180420e-01 -2.6746371388435364e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 246461 -8.0368496128357947e-05</internalNodes>
+      <leafValues>
+        4.1716831922531128e-01 -2.7044576406478882e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 108596 -6.3696934375911951e-05</internalNodes>
+      <leafValues>
+        3.7671375274658203e-01 -2.7032816410064697e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 245421 2.0331081468611956e-03</internalNodes>
+      <leafValues>
+        -1.3189475238323212e-01 5.3093689680099487e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 40372 -2.0152917131781578e-03</internalNodes>
+      <leafValues>
+        4.5387655496597290e-01 -1.7904897034168243e-01</leafValues></_></weakClassifiers></stage0>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage1.xml

@@ -0,0 +1,97 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage1>
+  <maxWeakCount>18</maxWeakCount>
+  <stageThreshold>-2.2356419563293457e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 137269 3.5721786320209503e-02</internalNodes>
+      <leafValues>
+        -8.2851815223693848e-01 2.8000000119209290e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 142174 -3.6094750976189971e-04</internalNodes>
+      <leafValues>
+        2.4915382266044617e-02 -5.3551429510116577e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 215413 -1.1375316535122693e-04</internalNodes>
+      <leafValues>
+        3.1486526131629944e-01 -2.4710687994956970e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 224761 -3.5335551365278661e-04</internalNodes>
+      <leafValues>
+        3.2411506772041321e-01 -2.3498490452766418e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 238747 4.7944716061465442e-04</internalNodes>
+      <leafValues>
+        -2.2902281582355499e-01 3.4468775987625122e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 246220 -4.4793059350922704e-04</internalNodes>
+      <leafValues>
+        3.4047979116439819e-01 -2.1840864419937134e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 113034 4.6267956495285034e-03</internalNodes>
+      <leafValues>
+        -9.7332894802093506e-02 4.7579625248908997e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 16248 -9.2588871717453003e-02</internalNodes>
+      <leafValues>
+        -6.8898922204971313e-01 8.3021469414234161e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 166659 3.5765618085861206e-03</internalNodes>
+      <leafValues>
+        -1.9036938250064850e-01 3.4180012345314026e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 204339 6.8716658279299736e-04</internalNodes>
+      <leafValues>
+        -2.2414414584636688e-01 2.7947312593460083e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 251412 -9.1684190556406975e-04</internalNodes>
+      <leafValues>
+        2.7941298484802246e-01 -2.2247926890850067e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 100689 -3.9664559153607115e-05</internalNodes>
+      <leafValues>
+        2.8013676404953003e-01 -2.2328113019466400e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 52052 6.7782774567604065e-04</internalNodes>
+      <leafValues>
+        -2.4015776813030243e-01 2.5099447369575500e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 125829 -7.6104377512820065e-05</internalNodes>
+      <leafValues>
+        2.5199088454246521e-01 -2.5058096647262573e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 17402 1.7731750849634409e-03</internalNodes>
+      <leafValues>
+        -9.1696187853813171e-02 6.5126633644104004e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 84779 2.3523923009634018e-02</internalNodes>
+      <leafValues>
+        9.1342791914939880e-02 -7.0370614528656006e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 127958 -4.5852430048398674e-05</internalNodes>
+      <leafValues>
+        2.4304977059364319e-01 -2.1866756677627563e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 20579 -2.4681646376848221e-02</internalNodes>
+      <leafValues>
+        -7.7663135528564453e-01 7.4296921491622925e-02</leafValues></_></weakClassifiers></stage1>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage10.xml

@@ -0,0 +1,132 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage10>
+  <maxWeakCount>25</maxWeakCount>
+  <stageThreshold>-1.6869484186172485e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 96571 7.0924319326877594e-02</internalNodes>
+      <leafValues>
+        -8.1994462013244629e-01 1.</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 211451 -1.4974229270592332e-04</internalNodes>
+      <leafValues>
+        -1.1758241057395935e-01 -4.7201058268547058e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 141638 3.6080325953662395e-03</internalNodes>
+      <leafValues>
+        4.1330125182867050e-02 -6.8413001298904419e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 260739 -2.5871666148304939e-03</internalNodes>
+      <leafValues>
+        -8.9964669942855835e-01 6.9614753127098083e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 75813 -4.1133843362331390e-02</internalNodes>
+      <leafValues>
+        -6.1500775814056396e-01 4.6938192099332809e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 178851 -2.9497970826923847e-03</internalNodes>
+      <leafValues>
+        -8.3436530828475952e-01 2.9146455228328705e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 210326 -5.7735620066523552e-04</internalNodes>
+      <leafValues>
+        2.7557626366615295e-01 -1.2707893550395966e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 241925 -1.4028936624526978e-02</internalNodes>
+      <leafValues>
+        -4.6028608083724976e-01 8.4722064435482025e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 218274 4.1358434827998281e-04</internalNodes>
+      <leafValues>
+        -1.4093543589115143e-01 2.6155048608779907e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 169584 -3.0473567545413971e-02</internalNodes>
+      <leafValues>
+        -1. 4.0315803140401840e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 88763 1.4575267210602760e-02</internalNodes>
+      <leafValues>
+        3.8805205374956131e-02 -7.4559742212295532e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 141750 1.6899744048714638e-02</internalNodes>
+      <leafValues>
+        3.0248673632740974e-02 -8.3421397209167480e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 62036 -5.3739710710942745e-03</internalNodes>
+      <leafValues>
+        2.9799327254295349e-01 -1.2415607273578644e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 239530 2.9609014745801687e-03</internalNodes>
+      <leafValues>
+        9.5846541225910187e-02 -4.0334972739219666e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 71918 3.9903301512822509e-05</internalNodes>
+      <leafValues>
+        -2.1197047829627991e-01 1.7651285231113434e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 259219 1.8096107523888350e-03</internalNodes>
+      <leafValues>
+        8.9069291949272156e-02 -3.9672231674194336e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 64928 2.6091135805472732e-04</internalNodes>
+      <leafValues>
+        -1.4153051376342773e-01 2.5023892521858215e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 50582 1.8506914377212524e-02</internalNodes>
+      <leafValues>
+        -5.3542323410511017e-02 5.8322525024414062e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 71695 2.8529744595289230e-03</internalNodes>
+      <leafValues>
+        5.1270022988319397e-02 -7.0068496465682983e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 178350 2.7587846852838993e-03</internalNodes>
+      <leafValues>
+        -1.0219432413578033e-01 3.6910691857337952e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 129090 -3.6322362720966339e-02</internalNodes>
+      <leafValues>
+        -6.7315280437469482e-01 4.7328371554613113e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 51129 6.0269095003604889e-02</internalNodes>
+      <leafValues>
+        7.0619069039821625e-02 -4.5421582460403442e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 216288 -4.1448007686994970e-04</internalNodes>
+      <leafValues>
+        1.8252155184745789e-01 -2.0072692632675171e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 58679 -2.0707501971628517e-04</internalNodes>
+      <leafValues>
+        1.8038362264633179e-01 -2.0538178086280823e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 224787 -5.8571517001837492e-04</internalNodes>
+      <leafValues>
+        -2.7538534998893738e-01 1.4320029318332672e-01</leafValues></_></weakClassifiers></stage10>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage11.xml

@@ -0,0 +1,167 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage11>
+  <maxWeakCount>32</maxWeakCount>
+  <stageThreshold>-1.7896902561187744e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 32452 -4.7133091837167740e-02</internalNodes>
+      <leafValues>
+        4.2857143282890320e-01 -8.2382941246032715e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 215419 2.6195761747658253e-03</internalNodes>
+      <leafValues>
+        -3.7672019004821777e-01 4.3707898259162903e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 469 3.0427183955907822e-02</internalNodes>
+      <leafValues>
+        1.0352122783660889e-01 -3.4346729516983032e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 255068 -1.9120122306048870e-03</internalNodes>
+      <leafValues>
+        3.6451905965805054e-01 -1.0693412274122238e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 86742 1.3114705216139555e-03</internalNodes>
+      <leafValues>
+        -1.1655144393444061e-01 2.9990902543067932e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 24671 2.1971259266138077e-03</internalNodes>
+      <leafValues>
+        -7.6001644134521484e-02 4.4725221395492554e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 32503 2.2854117560200393e-04</internalNodes>
+      <leafValues>
+        1.4555934071540833e-01 -2.2414052486419678e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 83431 -4.5445822179317474e-03</internalNodes>
+      <leafValues>
+        -3.0197197198867798e-01 1.3468547165393829e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 83539 5.8883884921669960e-03</internalNodes>
+      <leafValues>
+        1.3668270409107208e-01 -3.1120502948760986e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 26604 1.1808322742581367e-03</internalNodes>
+      <leafValues>
+        -1.1526107788085938e-01 3.4216529130935669e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 261322 -1.6436435980722308e-03</internalNodes>
+      <leafValues>
+        -4.1905170679092407e-01 9.3637369573116302e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 257196 -2.3696476127952337e-03</internalNodes>
+      <leafValues>
+        -2.3007759451866150e-01 1.4280727505683899e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 238875 -4.4369861483573914e-02</internalNodes>
+      <leafValues>
+        7.4352025985717773e-01 -5.0559245049953461e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 103145 4.9974736757576466e-03</internalNodes>
+      <leafValues>
+        -1.0043781995773315e-01 3.2680180668830872e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 185648 1.2083798646926880e-02</internalNodes>
+      <leafValues>
+        4.6589784324169159e-02 -7.8054052591323853e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 26998 7.7568374574184418e-02</internalNodes>
+      <leafValues>
+        -8.2063071429729462e-02 4.6172121167182922e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 54603 -8.1538448284845799e-05</internalNodes>
+      <leafValues>
+        1.6711825132369995e-01 -2.1475791931152344e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 218478 -2.9472250491380692e-02</internalNodes>
+      <leafValues>
+        4.1580915451049805e-01 -9.8012797534465790e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 44088 1.7975054681301117e-02</internalNodes>
+      <leafValues>
+        -7.6326847076416016e-02 4.4083654880523682e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 106563 -2.3075384087860584e-03</internalNodes>
+      <leafValues>
+        -2.8690218925476074e-01 1.2882740795612335e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 12482 2.0294969901442528e-02</internalNodes>
+      <leafValues>
+        3.7382163107395172e-02 -7.9564720392227173e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 142548 -5.7901972904801369e-03</internalNodes>
+      <leafValues>
+        -3.6529657244682312e-01 8.7574794888496399e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 211026 -3.1970075797289610e-03</internalNodes>
+      <leafValues>
+        2.3901936411857605e-01 -1.5367035567760468e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 197282 -5.9674552176147699e-04</internalNodes>
+      <leafValues>
+        1.8999226391315460e-01 -1.7269301414489746e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 188231 8.6614871397614479e-03</internalNodes>
+      <leafValues>
+        -1.2349863350391388e-01 2.8643012046813965e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 210966 -2.2389576770365238e-03</internalNodes>
+      <leafValues>
+        -3.8214731216430664e-01 8.1997677683830261e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 103736 6.8121239542961121e-02</internalNodes>
+      <leafValues>
+        1.1296532303094864e-01 -2.8388756513595581e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 84900 -8.2984417676925659e-03</internalNodes>
+      <leafValues>
+        -2.6428982615470886e-01 1.3602311909198761e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 169761 2.2398598492145538e-02</internalNodes>
+      <leafValues>
+        -1.2119100987911224e-01 3.1601995229721069e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 6195 2.7642603963613510e-03</internalNodes>
+      <leafValues>
+        1.2488999962806702e-01 -3.0403107404708862e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 3665 -5.7875402271747589e-03</internalNodes>
+      <leafValues>
+        2.9603359103202820e-01 -1.2167659401893616e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 253830 5.5077590513974428e-04</internalNodes>
+      <leafValues>
+        1.3039503991603851e-01 -2.6254484057426453e-01</leafValues></_></weakClassifiers></stage11>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage2.xml

@@ -0,0 +1,87 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage2>
+  <maxWeakCount>16</maxWeakCount>
+  <stageThreshold>-1.9701111316680908e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 255177 9.2837605625391006e-03</internalNodes>
+      <leafValues>
+        -8.3388704061508179e-01 -2.1875000000000000e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 57578 2.7330656303092837e-04</internalNodes>
+      <leafValues>
+        -4.9379840493202209e-01 3.8017470389604568e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 2800 -6.3476458308286965e-05</internalNodes>
+      <leafValues>
+        2.8940623998641968e-01 -2.4937078356742859e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 224209 2.7173478156328201e-04</internalNodes>
+      <leafValues>
+        -2.3994807898998260e-01 2.4954319000244141e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 220684 -5.3776137065142393e-04</internalNodes>
+      <leafValues>
+        2.7680993080139160e-01 -2.3288232088088989e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 33862 4.0818107663653791e-05</internalNodes>
+      <leafValues>
+        -2.2196719050407410e-01 2.8879314661026001e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 151015 -8.3656832575798035e-02</internalNodes>
+      <leafValues>
+        -7.6336216926574707e-01 1.2941515445709229e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 246261 -6.4269080758094788e-04</internalNodes>
+      <leafValues>
+        3.5352027416229248e-01 -1.9810034334659576e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 64171 -6.3427746295928955e-02</internalNodes>
+      <leafValues>
+        -5.7552325725555420e-01 1.3970251381397247e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 126699 1.7928556189872324e-04</internalNodes>
+      <leafValues>
+        -2.5303149223327637e-01 2.3289397358894348e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 35209 -4.3857514858245850e-01</internalNodes>
+      <leafValues>
+        -8.9680689573287964e-01 9.5759131014347076e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 250517 -1.7104612197726965e-04</internalNodes>
+      <leafValues>
+        2.3386283218860626e-01 -2.3413363099098206e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 30303 1.4779038727283478e-02</internalNodes>
+      <leafValues>
+        -8.4562897682189941e-02 6.1388427019119263e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 141779 1.2016045860946178e-02</internalNodes>
+      <leafValues>
+        1.1763860285282135e-01 -4.9125817418098450e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 190722 5.9710850473493338e-04</internalNodes>
+      <leafValues>
+        -2.2408641874790192e-01 2.5521871447563171e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 184219 -7.9119869042187929e-04</internalNodes>
+      <leafValues>
+        2.1977363526821136e-01 -2.4718604981899261e-01</leafValues></_></weakClassifiers></stage2>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage3.xml

@@ -0,0 +1,97 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage3>
+  <maxWeakCount>18</maxWeakCount>
+  <stageThreshold>-1.8751841783523560e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 244480 1.5861921012401581e-02</internalNodes>
+      <leafValues>
+        -8.2552206516265869e-01 5.0000000000000000e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 259083 -3.6250399425625801e-03</internalNodes>
+      <leafValues>
+        2.5654155015945435e-01 -4.0561401844024658e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 106550 -1.0207454860210419e-01</internalNodes>
+      <leafValues>
+        -7.3966819047927856e-01 5.0034116953611374e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 126099 1.3055585441179574e-05</internalNodes>
+      <leafValues>
+        2.4028410017490387e-01 -2.2227208316326141e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 257491 5.2861066069453955e-04</internalNodes>
+      <leafValues>
+        -1.8387256562709808e-01 2.5406163930892944e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 155198 -3.4884396940469742e-02</internalNodes>
+      <leafValues>
+        -6.7970168590545654e-01 4.9830660223960876e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 245305 -1.5093358233571053e-02</internalNodes>
+      <leafValues>
+        5.3967189788818359e-01 -8.5911646485328674e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 42420 -2.4146407842636108e-02</internalNodes>
+      <leafValues>
+        -6.2438166141510010e-01 6.9705188274383545e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 35391 -8.8775185868144035e-03</internalNodes>
+      <leafValues>
+        -4.6971791982650757e-01 1.1956012994050980e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 125851 -2.3658759891986847e-03</internalNodes>
+      <leafValues>
+        3.6748927831649780e-01 -1.5571966767311096e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 191247 -1.8085257033817470e-04</internalNodes>
+      <leafValues>
+        2.0363689959049225e-01 -2.3030610382556915e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 49673 1.1823540553450584e-03</internalNodes>
+      <leafValues>
+        -1.8798176944255829e-01 2.3848654329776764e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 82482 -3.1384633621200919e-04</internalNodes>
+      <leafValues>
+        2.2207137942314148e-01 -1.8694528937339783e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 35215 1.3226612936705351e-03</internalNodes>
+      <leafValues>
+        -1.7957177758216858e-01 2.7626475691795349e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 50010 -2.4914650712162256e-03</internalNodes>
+      <leafValues>
+        -4.8325034976005554e-01 1.0106151551008224e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 58641 -6.8913926370441914e-03</internalNodes>
+      <leafValues>
+        5.2059763669967651e-01 -9.7725525498390198e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 231037 9.9680703133344650e-03</internalNodes>
+      <leafValues>
+        -1.1073968559503555e-01 4.0598723292350769e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 154023 1.2397564202547073e-01</internalNodes>
+      <leafValues>
+        7.2054080665111542e-02 -7.0809888839721680e-01</leafValues></_></weakClassifiers></stage3>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage4.xml

@@ -0,0 +1,117 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage4>
+  <maxWeakCount>22</maxWeakCount>
+  <stageThreshold>-1.7902379035949707e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 216174 8.0151828005909920e-03</internalNodes>
+      <leafValues>
+        -8.1994462013244629e-01 1.</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 251036 -6.0034347698092461e-03</internalNodes>
+      <leafValues>
+        2.2075703740119934e-01 -3.7712317705154419e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 254441 2.2430909797549248e-02</internalNodes>
+      <leafValues>
+        3.3658131957054138e-02 -8.0483734607696533e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 35479 -6.3410094007849693e-03</internalNodes>
+      <leafValues>
+        -7.8173828125000000e-01 6.1298411339521408e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 122686 8.9281435066368431e-05</internalNodes>
+      <leafValues>
+        -1.6595298051834106e-01 2.2608807682991028e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 801 2.4483484029769897e-01</internalNodes>
+      <leafValues>
+        4.1919399052858353e-02 -8.8454484939575195e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 83269 -8.4756858646869659e-02</internalNodes>
+      <leafValues>
+        -9.7421234846115112e-01 1.8331680446863174e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 255569 -6.3373052398674190e-05</internalNodes>
+      <leafValues>
+        -1.9861432909965515e-01 1.7081585526466370e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 219507 7.3745205998420715e-02</internalNodes>
+      <leafValues>
+        4.7363422811031342e-02 -7.5348597764968872e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 243591 3.9508253335952759e-02</internalNodes>
+      <leafValues>
+        7.7703259885311127e-02 -4.3975996971130371e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 13350 -1.4824389945715666e-03</internalNodes>
+      <leafValues>
+        1.8207232654094696e-01 -1.9762933254241943e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 16462 5.0664367154240608e-04</internalNodes>
+      <leafValues>
+        -1.8743868172168732e-01 1.9797889888286591e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 155988 -5.0823288038372993e-03</internalNodes>
+      <leafValues>
+        4.8998206853866577e-01 -6.9998696446418762e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 188461 5.1610206719487906e-04</internalNodes>
+      <leafValues>
+        -1.8291656672954559e-01 1.9512335956096649e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 256193 4.0347880712943152e-05</internalNodes>
+      <leafValues>
+        -1.7262458801269531e-01 2.0465227961540222e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 233213 1.7419874668121338e-02</internalNodes>
+      <leafValues>
+        4.8033479601144791e-02 -7.4211651086807251e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 233500 -5.4605472832918167e-03</internalNodes>
+      <leafValues>
+        -4.6845641732215881e-01 7.2609759867191315e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 207765 -5.2535958820953965e-04</internalNodes>
+      <leafValues>
+        2.6859027147293091e-01 -1.7180655896663666e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 254383 -5.2848143968731165e-04</internalNodes>
+      <leafValues>
+        -2.7520981431007385e-01 1.3944891095161438e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 126351 2.5816308334469795e-03</internalNodes>
+      <leafValues>
+        7.8494705259799957e-02 -4.2257797718048096e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 244120 -5.8641433715820312e-03</internalNodes>
+      <leafValues>
+        2.7598381042480469e-01 -1.6063430905342102e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 181780 -1.4380576612893492e-04</internalNodes>
+      <leafValues>
+        2.0030431449413300e-01 -1.9603008031845093e-01</leafValues></_></weakClassifiers></stage4>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage5.xml

@@ -0,0 +1,107 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage5>
+  <maxWeakCount>20</maxWeakCount>
+  <stageThreshold>-1.6171981096267700e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 46275 3.6219112575054169e-02</internalNodes>
+      <leafValues>
+        -8.2306623458862305e-01 5.0000000000000000e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 1 7.7331520151346922e-04</internalNodes>
+      <leafValues>
+        -4.2411699891090393e-01 -1.4852857217192650e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 1506 1.8514251336455345e-02</internalNodes>
+      <leafValues>
+        5.9747643768787384e-02 -4.6825733780860901e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 24088 3.1934708356857300e-02</internalNodes>
+      <leafValues>
+        1.0872101783752441e-01 -3.3795773983001709e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 245072 4.1209971532225609e-03</internalNodes>
+      <leafValues>
+        -9.5931999385356903e-02 3.7004601955413818e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 77154 1.3252778444439173e-03</internalNodes>
+      <leafValues>
+        -1.7276380956172943e-01 1.9975538551807404e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 59889 3.7723220884799957e-02</internalNodes>
+      <leafValues>
+        6.2906742095947266e-02 -8.2433718442916870e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 260546 1.0423334315419197e-02</internalNodes>
+      <leafValues>
+        -6.4330548048019409e-02 5.5767643451690674e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 251278 3.7890626117587090e-03</internalNodes>
+      <leafValues>
+        7.2198309004306793e-02 -4.9710923433303833e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 72952 6.8704616278409958e-03</internalNodes>
+      <leafValues>
+        -1.0755266249179840e-01 3.3025455474853516e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 4825 5.8946676552295685e-02</internalNodes>
+      <leafValues>
+        5.6386210024356842e-02 -7.9343599081039429e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 67625 4.1175834834575653e-02</internalNodes>
+      <leafValues>
+        7.5439698994159698e-02 -3.6945250630378723e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 13284 1.2964900583028793e-02</internalNodes>
+      <leafValues>
+        9.7484521567821503e-02 -4.0200951695442200e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 116097 -1.1147938668727875e-02</internalNodes>
+      <leafValues>
+        -1. 2.7548771351575851e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 203534 -6.2119499780237675e-03</internalNodes>
+      <leafValues>
+        2.3965825140476227e-01 -1.4777071774005890e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 17494 -8.0058407038450241e-03</internalNodes>
+      <leafValues>
+        -5.7554775476455688e-01 6.5193727612495422e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 62425 4.9170171841979027e-03</internalNodes>
+      <leafValues>
+        -1.2465258687734604e-01 2.8955018520355225e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 190672 8.9359446428716183e-04</internalNodes>
+      <leafValues>
+        1.6018468141555786e-01 -2.4080280959606171e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 200301 -5.7871881872415543e-03</internalNodes>
+      <leafValues>
+        1.9334472715854645e-01 -1.9118192791938782e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 214612 -1.0445497464388609e-03</internalNodes>
+      <leafValues>
+        3.2018825411796570e-01 -1.1711678653955460e-01</leafValues></_></weakClassifiers></stage5>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage6.xml

@@ -0,0 +1,142 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage6>
+  <maxWeakCount>27</maxWeakCount>
+  <stageThreshold>-1.7677645683288574e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 38964 1.8302287906408310e-02</internalNodes>
+      <leafValues>
+        -8.2418602705001831e-01 4.7619048506021500e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 176439 -1.1286444962024689e-02</internalNodes>
+      <leafValues>
+        3.3364263176918030e-01 -3.7168881297111511e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 248719 2.4744385882513598e-05</internalNodes>
+      <leafValues>
+        1.5986821055412292e-01 -2.1441774070262909e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 18004 -2.1113080903887749e-02</internalNodes>
+      <leafValues>
+        3.9744469523429871e-01 -7.6052948832511902e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 181034 2.1192065905779600e-03</internalNodes>
+      <leafValues>
+        -1.1409001052379608e-01 2.7621039748191833e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 213272 -1.4461116865277290e-02</internalNodes>
+      <leafValues>
+        -7.7507328987121582e-01 4.6869516372680664e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 148022 -6.6964130382984877e-04</internalNodes>
+      <leafValues>
+        -2.0013764500617981e-01 1.5831212699413300e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 32485 3.3376570791006088e-03</internalNodes>
+      <leafValues>
+        -1.6484853625297546e-01 2.0312784612178802e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 170695 4.6336375176906586e-02</internalNodes>
+      <leafValues>
+        7.7525638043880463e-02 -7.4125880002975464e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 70614 4.6637351624667645e-03</internalNodes>
+      <leafValues>
+        -1.6918241977691650e-01 2.4887943267822266e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 51905 -4.5685209333896637e-03</internalNodes>
+      <leafValues>
+        3.2099020481109619e-01 -8.8494352996349335e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 186957 -3.9045535027980804e-02</internalNodes>
+      <leafValues>
+        6.1654996871948242e-01 -6.3212111592292786e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 203435 1.4315774897113442e-03</internalNodes>
+      <leafValues>
+        6.7997552454471588e-02 -4.9553343653678894e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 179352 2.4909505154937506e-03</internalNodes>
+      <leafValues>
+        4.4152159243822098e-02 -8.6444950103759766e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 251143 -9.5660910010337830e-03</internalNodes>
+      <leafValues>
+        4.6550533175468445e-01 -7.7225625514984131e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 191687 -6.1975524295121431e-04</internalNodes>
+      <leafValues>
+        1.7742143571376801e-01 -1.8629780411720276e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 145706 1.7433455213904381e-03</internalNodes>
+      <leafValues>
+        -1.5059350430965424e-01 2.0669434964656830e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 172067 -9.3545634299516678e-03</internalNodes>
+      <leafValues>
+        4.7877272963523865e-01 -7.3861926794052124e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 90854 -4.5494278892874718e-03</internalNodes>
+      <leafValues>
+        -3.0157461762428284e-01 1.1988414824008942e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 42323 -2.7183657512068748e-03</internalNodes>
+      <leafValues>
+        -3.7483543157577515e-01 8.5217326879501343e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 261577 -6.6327136009931564e-03</internalNodes>
+      <leafValues>
+        -8.9939653873443604e-01 3.1543768942356110e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 246010 3.0943896621465683e-02</internalNodes>
+      <leafValues>
+        -7.2363331913948059e-02 5.2534228563308716e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 26679 -2.3528675956185907e-04</internalNodes>
+      <leafValues>
+        -2.1258419752120972e-01 1.5342997014522552e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 232296 -1.1926303617656231e-02</internalNodes>
+      <leafValues>
+        -3.4165814518928528e-01 9.2051379382610321e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 14468 2.5930549018085003e-03</internalNodes>
+      <leafValues>
+        2.9644332826137543e-02 -9.2073792219161987e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 47008 -1.7857389757409692e-03</internalNodes>
+      <leafValues>
+        2.3626631498336792e-01 -1.4367222785949707e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 180071 -2.7333740144968033e-03</internalNodes>
+      <leafValues>
+        -3.2003125548362732e-01 1.0139349102973938e-01</leafValues></_></weakClassifiers></stage6>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage7.xml

@@ -0,0 +1,152 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage7>
+  <maxWeakCount>29</maxWeakCount>
+  <stageThreshold>-1.6923012733459473e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 204317 -3.5963267087936401e-02</internalNodes>
+      <leafValues>
+        5.0000000000000000e-01 -8.2306623458862305e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 178513 6.2072677537798882e-03</internalNodes>
+      <leafValues>
+        -4.0280604362487793e-01 8.5296377539634705e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 207209 -4.1107401251792908e-02</internalNodes>
+      <leafValues>
+        4.5381823182106018e-01 -9.3319684267044067e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 256936 4.7957309288904071e-04</internalNodes>
+      <leafValues>
+        -1.1351539194583893e-01 2.8576567769050598e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 207481 -1.3959359377622604e-02</internalNodes>
+      <leafValues>
+        3.5362941026687622e-01 -8.6558297276496887e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 245 1.2834025546908379e-02</internalNodes>
+      <leafValues>
+        -5.5092144757509232e-02 5.0871634483337402e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 137262 -3.4705869620665908e-04</internalNodes>
+      <leafValues>
+        2.1104402840137482e-01 -1.3990698754787445e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 214983 -1.0513635352253914e-03</internalNodes>
+      <leafValues>
+        -2.0770642161369324e-01 1.5086375176906586e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 188079 1.4868211001157761e-03</internalNodes>
+      <leafValues>
+        -1.2847360968589783e-01 2.2934591770172119e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 124237 -2.4880174547433853e-02</internalNodes>
+      <leafValues>
+        3.6084103584289551e-01 -9.7620248794555664e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 47122 4.8072505742311478e-03</internalNodes>
+      <leafValues>
+        1.4193618297576904e-01 -2.4843324720859528e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 142445 -7.5567420572042465e-03</internalNodes>
+      <leafValues>
+        -2.7613562345504761e-01 1.1317784339189529e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 95360 1.1754093691706657e-02</internalNodes>
+      <leafValues>
+        1.1661175638437271e-01 -3.1876373291015625e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 128072 -1.4386835391633213e-04</internalNodes>
+      <leafValues>
+        -2.0119401812553406e-01 1.9025532901287079e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 106150 6.5523679368197918e-03</internalNodes>
+      <leafValues>
+        6.4145371317863464e-02 -5.1194477081298828e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 74929 -1.0758183896541595e-02</internalNodes>
+      <leafValues>
+        6.1613875627517700e-01 -7.2691880166530609e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 181715 -4.1741915047168732e-03</internalNodes>
+      <leafValues>
+        2.4628119170665741e-01 -1.3857695460319519e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 58626 -8.9535377919673920e-03</internalNodes>
+      <leafValues>
+        -9.2645341157913208e-01 4.1388127952814102e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 181316 -8.1538539379835129e-03</internalNodes>
+      <leafValues>
+        3.2532292604446411e-01 -1.2642900645732880e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 176976 8.8271200656890869e-02</internalNodes>
+      <leafValues>
+        -5.8189079165458679e-02 5.7296651601791382e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 199219 -7.6730968430638313e-03</internalNodes>
+      <leafValues>
+        -4.4933944940567017e-01 8.1401504576206207e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 239881 1.3322687009349465e-03</internalNodes>
+      <leafValues>
+        1.4256893098354340e-01 -2.4609300494194031e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 192638 1.2328685261309147e-02</internalNodes>
+      <leafValues>
+        8.0757759511470795e-02 -4.1132536530494690e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 167347 1.0817053727805614e-02</internalNodes>
+      <leafValues>
+        -1.5686295926570892e-01 2.5130897760391235e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 7748 -2.6984363794326782e-03</internalNodes>
+      <leafValues>
+        4.4750407338142395e-01 -8.5524260997772217e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 127721 1.0616924613714218e-02</internalNodes>
+      <leafValues>
+        -7.6170556247234344e-02 4.6939194202423096e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 217209 2.9625549912452698e-02</internalNodes>
+      <leafValues>
+        4.8887573182582855e-02 -7.8176867961883545e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 93145 -5.1246671937406063e-03</internalNodes>
+      <leafValues>
+        -6.8288952112197876e-01 4.0251817554235458e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 194179 1.4695306890644133e-04</internalNodes>
+      <leafValues>
+        1.7425540089607239e-01 -2.0023734867572784e-01</leafValues></_></weakClassifiers></stage7>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage8.xml

@@ -0,0 +1,127 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage8>
+  <maxWeakCount>24</maxWeakCount>
+  <stageThreshold>-1.8167937994003296e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 75722 6.0299575328826904e-02</internalNodes>
+      <leafValues>
+        -8.3223372697830200e-01 -1.0204081982374191e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 43978 8.1636786460876465e-02</internalNodes>
+      <leafValues>
+        -4.1386893391609192e-01 3.3031061291694641e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 136437 -6.8148612626828253e-05</internalNodes>
+      <leafValues>
+        2.6524144411087036e-01 -2.4595353007316589e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 173175 3.4866763598984107e-05</internalNodes>
+      <leafValues>
+        -2.1400687098503113e-01 2.3822486400604248e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 113472 -2.1247303113341331e-02</internalNodes>
+      <leafValues>
+        6.1581319570541382e-01 -8.1494018435478210e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 180952 -2.7432952076196671e-02</internalNodes>
+      <leafValues>
+        6.0847622156143188e-01 -6.6269092261791229e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 261063 -3.6354072391986847e-02</internalNodes>
+      <leafValues>
+        -5.4442971944808960e-01 8.6072765290737152e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 110406 9.2946027871221304e-04</internalNodes>
+      <leafValues>
+        1.7772659659385681e-01 -2.5326943397521973e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 158582 -1.2942004948854446e-02</internalNodes>
+      <leafValues>
+        4.3233481049537659e-01 -1.1728420108556747e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 194254 1.5673905611038208e-02</internalNodes>
+      <leafValues>
+        -1.4792789518833160e-01 2.6766616106033325e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 103287 -1.1648360639810562e-02</internalNodes>
+      <leafValues>
+        2.5697246193885803e-01 -1.6770395636558533e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 217941 2.1497393026947975e-03</internalNodes>
+      <leafValues>
+        1.8686321377754211e-01 -2.3792789876461029e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 130622 -7.6546636410057545e-03</internalNodes>
+      <leafValues>
+        -6.7426544427871704e-01 6.7121498286724091e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 245900 1.0658910498023033e-02</internalNodes>
+      <leafValues>
+        -8.5903778672218323e-02 5.1432758569717407e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 46990 -4.7946855193004012e-04</internalNodes>
+      <leafValues>
+        -3.2262659072875977e-01 1.3103736937046051e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 37324 1.7581915482878685e-02</internalNodes>
+      <leafValues>
+        -5.7379148900508881e-02 6.7399263381958008e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 214303 4.4539461669046432e-05</internalNodes>
+      <leafValues>
+        -1.7566090822219849e-01 2.0616781711578369e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 85621 1.7850503325462341e-02</internalNodes>
+      <leafValues>
+        -1.1567226052284241e-01 3.0400106310844421e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 233014 4.2269509285688400e-03</internalNodes>
+      <leafValues>
+        1.4860102534294128e-01 -2.5009277462959290e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 112112 4.6986991947051138e-05</internalNodes>
+      <leafValues>
+        -1.6853319108486176e-01 2.1751406788825989e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 233046 7.3227880056947470e-04</internalNodes>
+      <leafValues>
+        1.5448771417140961e-01 -2.4861399829387665e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 66065 1.8825223669409752e-03</internalNodes>
+      <leafValues>
+        1.2523283064365387e-01 -3.2745039463043213e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 45029 1.2315854430198669e-02</internalNodes>
+      <leafValues>
+        -1.4746649563312531e-01 2.7224215865135193e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 200191 -5.8640458155423403e-04</internalNodes>
+      <leafValues>
+        -2.5190883874893188e-01 1.5949553251266479e-01</leafValues></_></weakClassifiers></stage8>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t1/stage9.xml

@@ -0,0 +1,142 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage9>
+  <maxWeakCount>27</maxWeakCount>
+  <stageThreshold>-1.8949035406112671e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 193220 2.6374928653240204e-02</internalNodes>
+      <leafValues>
+        -8.2998597621917725e-01 2.0000000298023224e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 26447 -1.2758189812302589e-02</internalNodes>
+      <leafValues>
+        2.4427592754364014e-01 -4.0791851282119751e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 92120 6.2989763915538788e-02</internalNodes>
+      <leafValues>
+        6.5899044275283813e-02 -5.0920766592025757e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 213958 -1.5275410842150450e-03</internalNodes>
+      <leafValues>
+        4.7397440671920776e-01 -9.0117275714874268e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 149175 1.1400219053030014e-02</internalNodes>
+      <leafValues>
+        -1.1058270931243896e-01 3.4998399019241333e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 129075 -9.1996341943740845e-02</internalNodes>
+      <leafValues>
+        -3.4550747275352478e-01 1.5364947915077209e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 39182 4.1233282536268234e-03</internalNodes>
+      <leafValues>
+        8.1491999328136444e-02 -3.4329697489738464e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 19274 -1.2714721262454987e-02</internalNodes>
+      <leafValues>
+        -2.9831326007843018e-01 1.4976705610752106e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 3292 1.4548556506633759e-01</internalNodes>
+      <leafValues>
+        9.6385650336742401e-02 -5.1930439472198486e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 221112 1.9064375010202639e-05</internalNodes>
+      <leafValues>
+        -2.0087321102619171e-01 2.1022908389568329e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 124603 2.6916436851024628e-02</internalNodes>
+      <leafValues>
+        8.0602176487445831e-02 -5.4292464256286621e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 12817 1.2030512094497681e-01</internalNodes>
+      <leafValues>
+        -1.1729680001735687e-01 3.3879375457763672e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 82264 -6.6397637128829956e-03</internalNodes>
+      <leafValues>
+        -7.6249617338180542e-01 4.4772326946258545e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 113596 -3.6568228097166866e-05</internalNodes>
+      <leafValues>
+        2.3451969027519226e-01 -1.9039800763130188e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 33846 7.1600684896111488e-04</internalNodes>
+      <leafValues>
+        1.5461087226867676e-01 -2.3816385865211487e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 231517 -1.6735833138227463e-02</internalNodes>
+      <leafValues>
+        -5.6783968210220337e-01 5.7796332985162735e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 125899 1.4016887871548533e-03</internalNodes>
+      <leafValues>
+        1.0557589679956436e-01 -3.4124493598937988e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 139986 6.8018147721886635e-03</internalNodes>
+      <leafValues>
+        -8.9089885354042053e-02 4.4545269012451172e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 209282 5.7046175934374332e-03</internalNodes>
+      <leafValues>
+        -1.5976928174495697e-01 2.2061206400394440e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 12159 1.7986872792243958e-01</internalNodes>
+      <leafValues>
+        4.9089763313531876e-02 -7.7573937177658081e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 79679 -6.8783163442276418e-05</internalNodes>
+      <leafValues>
+        1.9441816210746765e-01 -1.8774586915969849e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 222809 2.1578925661742687e-03</internalNodes>
+      <leafValues>
+        1.0743179172277451e-01 -3.1742632389068604e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 178199 -1.8487831111997366e-03</internalNodes>
+      <leafValues>
+        2.1640789508819580e-01 -2.0860941708087921e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 12986 1.5235682949423790e-02</internalNodes>
+      <leafValues>
+        -1.2225846946239471e-01 3.2174721360206604e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 56081 3.4225359559059143e-02</internalNodes>
+      <leafValues>
+        -1.2926591932773590e-01 3.2870480418205261e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 79160 -4.0579801425337791e-03</internalNodes>
+      <leafValues>
+        -3.4456422924995422e-01 1.3334606587886810e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 3982 -8.9771389961242676e-02</internalNodes>
+      <leafValues>
+        2.9667279124259949e-01 -1.6828033328056335e-01</leafValues></_></weakClassifiers></stage9>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/cascade.xml

@@ -0,0 +1,674 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>12</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-6.9857284426689148e-02</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 24 7.3132544755935669e-02</internalNodes>
+          <leafValues>
+            -9.4999998807907104e-01 9.3181818723678589e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 46 8.3311080932617188e-02</internalNodes>
+          <leafValues>
+            -9.0652203559875488e-01 8.8014268875122070e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.0008283853530884e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 6 -1.1832243949174881e-01</internalNodes>
+          <leafValues>
+            6.5957444906234741e-01 -8.7628865242004395e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 31 1.2765679508447647e-02</internalNodes>
+          <leafValues>
+            -7.8486323356628418e-01 6.1405700445175171e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 42 6.1872858554124832e-02</internalNodes>
+          <leafValues>
+            -7.3859679698944092e-01 6.7582374811172485e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.0523968935012817e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 20 -5.7852640748023987e-02</internalNodes>
+          <leafValues>
+            4.2056074738502502e-01 -8.4530389308929443e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 41 -4.0381100028753281e-02</internalNodes>
+          <leafValues>
+            6.6613984107971191e-01 -6.6914182901382446e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 4.3017961084842682e-02</internalNodes>
+          <leafValues>
+            -8.4719657897949219e-01 4.6204876899719238e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-7.1327447891235352e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 21 3.5173662006855011e-02</internalNodes>
+          <leafValues>
+            -9.1812866926193237e-01 4.1880342364311218e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 3 2.9779970645904541e-03</internalNodes>
+          <leafValues>
+            -8.9671385288238525e-01 4.9135905504226685e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 43 1.0506974160671234e-01</internalNodes>
+          <leafValues>
+            -7.1667867898941040e-01 6.5290194749832153e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 19 -1.7827928066253662e-02</internalNodes>
+          <leafValues>
+            4.8131462931632996e-01 -8.8741576671600342e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.0446274280548096e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 7 2.7196373790502548e-02</internalNodes>
+          <leafValues>
+            -8.6826348304748535e-01 3.0578511953353882e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 6.4487643539905548e-02</internalNodes>
+          <leafValues>
+            -5.9504520893096924e-01 6.7478001117706299e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 2.4889567866921425e-03</internalNodes>
+          <leafValues>
+            -7.5536733865737915e-01 4.8187285661697388e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-5.6323349475860596e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 23 -1.0600250959396362e-01</internalNodes>
+          <leafValues>
+            8.4313726425170898e-01 -6.3713079690933228e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 1.9594368338584900e-01</internalNodes>
+          <leafValues>
+            -6.8043452501296997e-01 5.4470825195312500e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 38 -2.2170819342136383e-02</internalNodes>
+          <leafValues>
+            4.5749467611312866e-01 -7.6138621568679810e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 8.3648981526494026e-03</internalNodes>
+          <leafValues>
+            -9.2820900678634644e-01 2.9683715105056763e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.1174263954162598e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 8 2.6116007566452026e-01</internalNodes>
+          <leafValues>
+            -7.5789475440979004e-01 3.6734694242477417e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 -5.3467126563191414e-03</internalNodes>
+          <leafValues>
+            5.5447220802307129e-01 -6.3109600543975830e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 1.2671231292188168e-02</internalNodes>
+          <leafValues>
+            -6.8555009365081787e-01 4.3052643537521362e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 45 -6.4184088259935379e-03</internalNodes>
+          <leafValues>
+            5.7122170925140381e-01 -5.9808850288391113e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 2.2593162953853607e-02</internalNodes>
+          <leafValues>
+            -8.5607987642288208e-01 4.3912649154663086e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-9.2381137609481812e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 17 1.8414466083049774e-01</internalNodes>
+          <leafValues>
+            -7.3404252529144287e-01 3.0000001192092896e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 40 1.4040502905845642e-01</internalNodes>
+          <leafValues>
+            -5.2232235670089722e-01 5.7304370403289795e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 1.0363029316067696e-02</internalNodes>
+          <leafValues>
+            -5.7177013158798218e-01 5.4220241308212280e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 28 -5.4269127547740936e-02</internalNodes>
+          <leafValues>
+            5.9223252534866333e-01 -5.5288833379745483e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 2 5.2523061633110046e-02</internalNodes>
+          <leafValues>
+            -7.8327494859695435e-01 4.2789927124977112e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-5.2678936719894409e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 26 -2.7845047414302826e-02</internalNodes>
+          <leafValues>
+            7.1428573131561279e-01 -5.9832638502120972e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 -3.9416522486135364e-04</internalNodes>
+          <leafValues>
+            -9.2486000061035156e-01 2.7400460839271545e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 11 1.0721801221370697e-01</internalNodes>
+          <leafValues>
+            -7.2711890935897827e-01 3.0229723453521729e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 25 -1.0302538052201271e-02</internalNodes>
+          <leafValues>
+            6.9409972429275513e-01 -4.2416870594024658e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>6</maxWeakCount>
+      <stageThreshold>-1.4493153095245361e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 10 2.4479243159294128e-01</internalNodes>
+          <leafValues>
+            -6.5740740299224854e-01 4.7222220897674561e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 3.7433374673128128e-03</internalNodes>
+          <leafValues>
+            -5.6935876607894897e-01 4.9817276000976562e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 44 -2.8475340455770493e-02</internalNodes>
+          <leafValues>
+            5.4433584213256836e-01 -4.8710265755653381e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 47 -3.1239273957908154e-03</internalNodes>
+          <leafValues>
+            4.6561488509178162e-01 -5.2121520042419434e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 34 9.1940350830554962e-03</internalNodes>
+          <leafValues>
+            -4.9664518237113953e-01 5.2496069669723511e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 4 1.1519105173647404e-02</internalNodes>
+          <leafValues>
+            -7.3585474491119385e-01 3.6338412761688232e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-8.8048666715621948e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 13 2.7959531173110008e-02</internalNodes>
+          <leafValues>
+            -6.3888889551162720e-01 4.1666665673255920e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 -1.4312742277979851e-02</internalNodes>
+          <leafValues>
+            4.8493552207946777e-01 -5.4626697301864624e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 36 -1.9462900236248970e-02</internalNodes>
+          <leafValues>
+            4.8587536811828613e-01 -5.7627987861633301e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 14 4.8883416457101703e-04</internalNodes>
+          <leafValues>
+            -6.8754994869232178e-01 3.4999880194664001e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 39 -6.8803662434220314e-03</internalNodes>
+          <leafValues>
+            5.3095024824142456e-01 -4.6870502829551697e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.0835331678390503e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 18 2.0331215113401413e-02</internalNodes>
+          <leafValues>
+            -7.6623374223709106e-01 7.4626863002777100e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 48 3.1020954251289368e-02</internalNodes>
+          <leafValues>
+            -5.4749816656112671e-01 4.0196087956428528e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 30 -1.4530843123793602e-02</internalNodes>
+          <leafValues>
+            4.0155622363090515e-01 -5.7374048233032227e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 35 -1.1550894007086754e-02</internalNodes>
+          <leafValues>
+            7.9867005348205566e-01 -2.6203200221061707e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 15 2.0659237634390593e-05</internalNodes>
+          <leafValues>
+            -7.5018608570098877e-01 3.3275553584098816e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 1 2 -1.</_>
+        <_>
+          0 1 1 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 2 20 -1.</_>
+        <_>
+          1 0 1 20 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 3 20 -1.</_>
+        <_>
+          0 5 3 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 8 1 -1.</_>
+        <_>
+          4 0 4 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 10 1 -1.</_>
+        <_>
+          5 0 5 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 1 -1.</_>
+        <_>
+          5 0 10 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 9 -1.</_>
+        <_>
+          0 3 20 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 12 2 -1.</_>
+        <_>
+          6 3 6 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 19 12 -1.</_>
+        <_>
+          0 7 19 4 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 20 8 -1.</_>
+        <_>
+          0 7 20 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 18 16 -1.</_>
+        <_>
+          9 4 9 16 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 19 6 -1.</_>
+        <_>
+          0 7 19 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 7 2 13 -1.</_>
+        <_>
+          1 7 1 13 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 8 8 4 -1.</_>
+        <_>
+          2 8 4 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 16 2 4 -1.</_>
+        <_>
+          1 16 1 4 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 19 4 1 -1.</_>
+        <_>
+          2 19 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 2 4 3 -1.</_>
+        <_>
+          1 3 4 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 6 15 -1.</_>
+        <_>
+          3 8 2 5 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 3 16 1 -1.</_>
+        <_>
+          5 3 8 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          1 9 5 10 -1.</_>
+        <_>
+          1 14 5 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 0 8 14 -1.</_>
+        <_>
+          2 0 4 7 2.</_>
+        <_>
+          6 7 4 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 2 3 10 -1.</_>
+        <_>
+          2 7 3 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 2 15 3 -1.</_>
+        <_>
+          3 3 15 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 6 9 13 -1.</_>
+        <_>
+          6 6 3 13 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 0 12 8 -1.</_>
+        <_>
+          8 0 4 8 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 16 8 3 -1.</_>
+        <_>
+          4 17 8 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 5 6 4 -1.</_>
+        <_>
+          7 5 2 4 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 8 12 -1.</_>
+        <_>
+          8 0 4 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 2 6 3 -1.</_>
+        <_>
+          6 2 3 3 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 11 10 9 -1.</_>
+        <_>
+          11 11 5 9 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 4 4 -1.</_>
+        <_>
+          6 2 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 6 2 -1.</_>
+        <_>
+          9 3 2 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 9 6 1 -1.</_>
+        <_>
+          9 9 2 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 9 6 3 -1.</_>
+        <_>
+          9 10 2 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 2 12 -1.</_>
+        <_>
+          9 0 1 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 16 4 4 -1.</_>
+        <_>
+          8 17 4 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 0 4 8 -1.</_>
+        <_>
+          11 0 2 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 1 10 12 -1.</_>
+        <_>
+          9 1 5 6 2.</_>
+        <_>
+          14 7 5 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 2 6 6 -1.</_>
+        <_>
+          12 2 3 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 9 8 2 -1.</_>
+        <_>
+          12 9 4 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 4 8 8 -1.</_>
+        <_>
+          11 4 8 4 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 1 7 6 -1.</_>
+        <_>
+          13 3 7 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 2 4 16 -1.</_>
+        <_>
+          14 6 4 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 4 6 12 -1.</_>
+        <_>
+          16 8 2 4 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 1 3 6 -1.</_>
+        <_>
+          16 3 1 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 2 3 3 -1.</_>
+        <_>
+          16 3 1 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 0 4 12 -1.</_>
+        <_>
+          12 4 4 4 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          18 8 2 12 -1.</_>
+        <_>
+          19 8 1 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          19 6 1 12 -1.</_>
+        <_>
+          19 6 1 6 2.</_></rects>
+      <tilted>1</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/params.xml

@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<params>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams></params>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage0.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage0>
+  <maxWeakCount>2</maxWeakCount>
+  <stageThreshold>-6.9857284426689148e-02</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 38344 7.3132544755935669e-02</internalNodes>
+      <leafValues>
+        -9.4999998807907104e-01 9.3181818723678589e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 118673 8.3311080932617188e-02</internalNodes>
+      <leafValues>
+        -9.0652203559875488e-01 8.8014268875122070e-01</leafValues></_></weakClassifiers></stage0>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage1.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage1>
+  <maxWeakCount>3</maxWeakCount>
+  <stageThreshold>-1.0008283853530884e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 962 -1.1832243949174881e-01</internalNodes>
+      <leafValues>
+        6.5957444906234741e-01 -8.7628865242004395e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 66537 1.2765679508447647e-02</internalNodes>
+      <leafValues>
+        -7.8486323356628418e-01 6.1405700445175171e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 111620 6.1872858554124832e-02</internalNodes>
+      <leafValues>
+        -7.3859679698944092e-01 6.7582374811172485e-01</leafValues></_></weakClassifiers></stage1>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage10.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage10>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-8.8048666715621948e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 6445 2.7959531173110008e-02</internalNodes>
+      <leafValues>
+        -6.3888889551162720e-01 4.1666665673255920e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 31369 -1.4312742277979851e-02</internalNodes>
+      <leafValues>
+        4.8493552207946777e-01 -5.4626697301864624e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 80232 -1.9462900236248970e-02</internalNodes>
+      <leafValues>
+        4.8587536811828613e-01 -5.7627987861633301e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 9562 4.8883416457101703e-04</internalNodes>
+      <leafValues>
+        -6.8754994869232178e-01 3.4999880194664001e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 91971 -6.8803662434220314e-03</internalNodes>
+      <leafValues>
+        5.3095024824142456e-01 -4.6870502829551697e-01</leafValues></_></weakClassifiers></stage10>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage11.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage11>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-1.0835331678390503e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 12823 2.0331215113401413e-02</internalNodes>
+      <leafValues>
+        -7.6623374223709106e-01 7.4626863002777100e-02</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 125038 3.1020954251289368e-02</internalNodes>
+      <leafValues>
+        -5.4749816656112671e-01 4.0196087956428528e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 65314 -1.4530843123793602e-02</internalNodes>
+      <leafValues>
+        4.0155622363090515e-01 -5.7374048233032227e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 79830 -1.1550894007086754e-02</internalNodes>
+      <leafValues>
+        7.9867005348205566e-01 -2.6203200221061707e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 9930 2.0659237634390593e-05</internalNodes>
+      <leafValues>
+        -7.5018608570098877e-01 3.3275553584098816e-01</leafValues></_></weakClassifiers></stage11>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage2.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage2>
+  <maxWeakCount>3</maxWeakCount>
+  <stageThreshold>-1.0523968935012817e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 19725 -5.7852640748023987e-02</internalNodes>
+      <leafValues>
+        4.2056074738502502e-01 -8.4530389308929443e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 106510 -4.0381100028753281e-02</internalNodes>
+      <leafValues>
+        6.6613984107971191e-01 -6.6914182901382446e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 55982 4.3017961084842682e-02</internalNodes>
+      <leafValues>
+        -8.4719657897949219e-01 4.6204876899719238e-01</leafValues></_></weakClassifiers></stage2>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage3.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage3>
+  <maxWeakCount>4</maxWeakCount>
+  <stageThreshold>-7.1327447891235352e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 21398 3.5173662006855011e-02</internalNodes>
+      <leafValues>
+        -9.1812866926193237e-01 4.1880342364311218e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 291 2.9779970645904541e-03</internalNodes>
+      <leafValues>
+        -8.9671385288238525e-01 4.9135905504226685e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 112262 1.0506974160671234e-01</internalNodes>
+      <leafValues>
+        -7.1667867898941040e-01 6.5290194749832153e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 16772 -1.7827928066253662e-02</internalNodes>
+      <leafValues>
+        4.8131462931632996e-01 -8.8741576671600342e-01</leafValues></_></weakClassifiers></stage3>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage4.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage4>
+  <maxWeakCount>3</maxWeakCount>
+  <stageThreshold>-1.0446274280548096e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 3177 2.7196373790502548e-02</internalNodes>
+      <leafValues>
+        -8.6826348304748535e-01 3.0578511953353882e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 62842 6.4487643539905548e-02</internalNodes>
+      <leafValues>
+        -5.9504520893096924e-01 6.7478001117706299e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 5800 2.4889567866921425e-03</internalNodes>
+      <leafValues>
+        -7.5536733865737915e-01 4.8187285661697388e-01</leafValues></_></weakClassifiers></stage4>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage5.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage5>
+  <maxWeakCount>4</maxWeakCount>
+  <stageThreshold>-5.6323349475860596e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 33773 -1.0600250959396362e-01</internalNodes>
+      <leafValues>
+        8.4313726425170898e-01 -6.3713079690933228e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 3564 1.9594368338584900e-01</internalNodes>
+      <leafValues>
+        -6.8043452501296997e-01 5.4470825195312500e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 81656 -2.2170819342136383e-02</internalNodes>
+      <leafValues>
+        4.5749467611312866e-01 -7.6138621568679810e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 392 8.3648981526494026e-03</internalNodes>
+      <leafValues>
+        -9.2820900678634644e-01 2.9683715105056763e-01</leafValues></_></weakClassifiers></stage5>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage6.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage6>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-1.1174263954162598e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 3548 2.6116007566452026e-01</internalNodes>
+      <leafValues>
+        -7.5789475440979004e-01 3.6734694242477417e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 12006 -5.3467126563191414e-03</internalNodes>
+      <leafValues>
+        5.5447220802307129e-01 -6.3109600543975830e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 69940 1.2671231292188168e-02</internalNodes>
+      <leafValues>
+        -6.8555009365081787e-01 4.3052643537521362e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 115596 -6.4184088259935379e-03</internalNodes>
+      <leafValues>
+        5.7122170925140381e-01 -5.9808850288391113e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 81164 2.2593162953853607e-02</internalNodes>
+      <leafValues>
+        -8.5607987642288208e-01 4.3912649154663086e-01</leafValues></_></weakClassifiers></stage6>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage7.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage7>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-9.2381137609481812e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 12692 1.8414466083049774e-01</internalNodes>
+      <leafValues>
+        -7.3404252529144287e-01 3.0000001192092896e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 96486 1.4040502905845642e-01</internalNodes>
+      <leafValues>
+        -5.2232235670089722e-01 5.7304370403289795e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 94 1.0363029316067696e-02</internalNodes>
+      <leafValues>
+        -5.7177013158798218e-01 5.4220241308212280e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 57644 -5.4269127547740936e-02</internalNodes>
+      <leafValues>
+        5.9223252534866333e-01 -5.5288833379745483e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 231 5.2523061633110046e-02</internalNodes>
+      <leafValues>
+        -7.8327494859695435e-01 4.2789927124977112e-01</leafValues></_></weakClassifiers></stage7>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage8.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage8>
+  <maxWeakCount>4</maxWeakCount>
+  <stageThreshold>-5.2678936719894409e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 51133 -2.7845047414302826e-02</internalNodes>
+      <leafValues>
+        7.1428573131561279e-01 -5.9832638502120972e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 1 -3.9416522486135364e-04</internalNodes>
+      <leafValues>
+        -9.2486000061035156e-01 2.7400460839271545e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 4330 1.0721801221370697e-01</internalNodes>
+      <leafValues>
+        -7.2711890935897827e-01 3.0229723453521729e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 46957 -1.0302538052201271e-02</internalNodes>
+      <leafValues>
+        6.9409972429275513e-01 -4.2416870594024658e-01</leafValues></_></weakClassifiers></stage8>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t2/stage9.xml

@@ -0,0 +1,37 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage9>
+  <maxWeakCount>6</maxWeakCount>
+  <stageThreshold>-1.4493153095245361e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 4146 2.4479243159294128e-01</internalNodes>
+      <leafValues>
+        -6.5740740299224854e-01 4.7222220897674561e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 69935 3.7433374673128128e-03</internalNodes>
+      <leafValues>
+        -5.6935876607894897e-01 4.9817276000976562e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 115281 -2.8475340455770493e-02</internalNodes>
+      <leafValues>
+        5.4433584213256836e-01 -4.8710265755653381e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 124429 -3.1239273957908154e-03</internalNodes>
+      <leafValues>
+        4.6561488509178162e-01 -5.2121520042419434e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 72193 9.1940350830554962e-03</internalNodes>
+      <leafValues>
+        -4.9664518237113953e-01 5.2496069669723511e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 388 1.1519105173647404e-02</internalNodes>
+      <leafValues>
+        -7.3585474491119385e-01 3.6338412761688232e-01</leafValues></_></weakClassifiers></stage9>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/cascade.xml

@@ -0,0 +1,658 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<cascade>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams>
+  <stageNum>14</stageNum>
+  <stages>
+    <!-- stage 0 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-1.5131105482578278e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 15 7.3132544755935669e-02</internalNodes>
+          <leafValues>
+            -9.6969699859619141e-01 8.7999999523162842e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 22 3.7634912878274918e-02</internalNodes>
+          <leafValues>
+            -9.7909134626388550e-01 8.1838589906692505e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 1 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.9654263257980347e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 3 2.1198132634162903e-01</internalNodes>
+          <leafValues>
+            -9.3999999761581421e-01 8.3333331346511841e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 27 -5.1079854369163513e-02</internalNodes>
+          <leafValues>
+            7.5422900915145874e-01 -8.4309655427932739e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 42 3.2548047602176666e-02</internalNodes>
+          <leafValues>
+            -8.1077164411544800e-01 8.0424255132675171e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 2 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-8.4922987222671509e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 36 6.5322615206241608e-02</internalNodes>
+          <leafValues>
+            -8.7939697504043579e-01 5.5102038383483887e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 4 1.9205823540687561e-01</internalNodes>
+          <leafValues>
+            -7.1354663372039795e-01 7.1951913833618164e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 34 -1.0098288208246231e-01</internalNodes>
+          <leafValues>
+            7.4371367692947388e-01 -6.5768426656723022e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 3 -->
+    <_>
+      <maxWeakCount>2</maxWeakCount>
+      <stageThreshold>-5.2841639518737793e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 2 2.3883845657110214e-02</internalNodes>
+          <leafValues>
+            -8.3756345510482788e-01 3.3333334326744080e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 41 1.0589134693145752e-01</internalNodes>
+          <leafValues>
+            -8.6174976825714111e-01 3.8202732801437378e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 4 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.0350991487503052e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 14 -9.1196425259113312e-02</internalNodes>
+          <leafValues>
+            6.2162160873413086e-01 -8.1042653322219849e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 9 8.7607488036155701e-02</internalNodes>
+          <leafValues>
+            -7.8688693046569824e-01 6.2912172079086304e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 24 5.6541308760643005e-02</internalNodes>
+          <leafValues>
+            -6.6161835193634033e-01 6.9380360841751099e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 5 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-9.5506101846694946e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 11 8.9198779314756393e-03</internalNodes>
+          <leafValues>
+            -7.6958525180816650e-01 6.1290323734283447e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 45 -3.1269099563360214e-03</internalNodes>
+          <leafValues>
+            5.1104712486267090e-01 -7.0055544376373291e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 7 -9.2323711141943932e-03</internalNodes>
+          <leafValues>
+            5.3979915380477905e-01 -6.9652289152145386e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 6 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2330348491668701e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 0 1.1109821498394012e-02</internalNodes>
+          <leafValues>
+            -8.7356323003768921e-01 5.4054055362939835e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 40 -7.7119180932641029e-03</internalNodes>
+          <leafValues>
+            5.3126132488250732e-01 -6.4888054132461548e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 1 1.6299208626151085e-02</internalNodes>
+          <leafValues>
+            -8.9073300361633301e-01 3.8267943263053894e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 7 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-6.9402027130126953e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 25 6.2881767749786377e-02</internalNodes>
+          <leafValues>
+            -7.6255708932876587e-01 6.5517240762710571e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 29 -1.2179381214082241e-02</internalNodes>
+          <leafValues>
+            8.1599736213684082e-01 -5.0710964202880859e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 23 1.5992985665798187e-01</internalNodes>
+          <leafValues>
+            -7.4746054410934448e-01 6.2096637487411499e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 8 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.2014210224151611e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 39 1.9785316661000252e-02</internalNodes>
+          <leafValues>
+            -7.2687226533889771e-01 8.0952382087707520e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 5 5.5234711617231369e-03</internalNodes>
+          <leafValues>
+            -8.0144739151000977e-01 3.9590144157409668e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 6 -1.4743935316801071e-02</internalNodes>
+          <leafValues>
+            4.0145263075828552e-01 -7.5309175252914429e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 31 3.2769851386547089e-02</internalNodes>
+          <leafValues>
+            -6.3974779844284058e-01 4.9125114083290100e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 37 2.0255863666534424e-02</internalNodes>
+          <leafValues>
+            -5.6580519676208496e-01 6.1177313327789307e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 9 -->
+    <_>
+      <maxWeakCount>3</maxWeakCount>
+      <stageThreshold>-1.2738654613494873e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 21 4.2292900383472443e-02</internalNodes>
+          <leafValues>
+            -8.0952382087707520e-01 8.4745764732360840e-02</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 12 4.2784538120031357e-02</internalNodes>
+          <leafValues>
+            -8.4340584278106689e-01 2.2612237930297852e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 8 -3.0783289112150669e-03</internalNodes>
+          <leafValues>
+            3.2863748073577881e-01 -6.9046407938003540e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 10 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.8541038036346436e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 30 -2.0627105608582497e-02</internalNodes>
+          <leafValues>
+            6.0606062412261963e-02 -8.3516484498977661e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 18 9.9415913224220276e-02</internalNodes>
+          <leafValues>
+            -6.4717310667037964e-01 5.1321762800216675e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 35 -2.8571443632245064e-02</internalNodes>
+          <leafValues>
+            3.8076385855674744e-01 -7.0071691274642944e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 0 1.7725368961691856e-02</internalNodes>
+          <leafValues>
+            -4.7960722446441650e-01 6.6265738010406494e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 11 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-1.3034328222274780e+00</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 13 -6.2260786071419716e-03</internalNodes>
+          <leafValues>
+            1.5384615957736969e-01 -7.9591834545135498e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 44 -4.6867121011018753e-02</internalNodes>
+          <leafValues>
+            3.6055722832679749e-01 -5.8249193429946899e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 43 -1.9795228727161884e-03</internalNodes>
+          <leafValues>
+            5.0797051191329956e-01 -5.0618976354598999e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 17 3.5088375210762024e-02</internalNodes>
+          <leafValues>
+            -7.3651200532913208e-01 4.1671240329742432e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 19 1.5235868049785495e-03</internalNodes>
+          <leafValues>
+            3.0445036292076111e-01 -8.4970545768737793e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 12 -->
+    <_>
+      <maxWeakCount>4</maxWeakCount>
+      <stageThreshold>-6.6577988862991333e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 28 -2.0102638751268387e-02</internalNodes>
+          <leafValues>
+            7.1428573131561279e-01 -7.1806168556213379e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 38 6.5985828638076782e-02</internalNodes>
+          <leafValues>
+            -7.8912955522537231e-01 2.9239723086357117e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 13 -1.4360356144607067e-03</internalNodes>
+          <leafValues>
+            3.3544215559959412e-01 -7.7690732479095459e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 20 3.7629939615726471e-02</internalNodes>
+          <leafValues>
+            -5.7326024770736694e-01 5.3679192066192627e-01</leafValues></_></weakClassifiers></_>
+    <!-- stage 13 -->
+    <_>
+      <maxWeakCount>5</maxWeakCount>
+      <stageThreshold>-7.6405721902847290e-01</stageThreshold>
+      <weakClassifiers>
+        <_>
+          <internalNodes>
+            0 -1 10 -1.8220141530036926e-02</internalNodes>
+          <leafValues>
+            1. -6.8510639667510986e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 26 -1.2162408791482449e-02</internalNodes>
+          <leafValues>
+            6.5581905841827393e-01 -5.0600630044937134e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 33 -4.4847460230812430e-04</internalNodes>
+          <leafValues>
+            3.7500736117362976e-01 -8.8655352592468262e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 16 6.7975055426359177e-03</internalNodes>
+          <leafValues>
+            -4.7455802559852600e-01 6.2044888734817505e-01</leafValues></_>
+        <_>
+          <internalNodes>
+            0 -1 32 8.3894869312644005e-03</internalNodes>
+          <leafValues>
+            -4.6866527199745178e-01 7.1337395906448364e-01</leafValues></_></weakClassifiers></_></stages>
+  <features>
+    <_>
+      <rects>
+        <_>
+          0 0 2 20 -1.</_>
+        <_>
+          1 0 1 20 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 0 20 2 -1.</_>
+        <_>
+          5 0 10 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 12 1 -1.</_>
+        <_>
+          6 3 6 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 3 19 12 -1.</_>
+        <_>
+          0 7 19 4 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 4 6 15 -1.</_>
+        <_>
+          2 9 2 5 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 10 2 10 -1.</_>
+        <_>
+          1 10 1 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 10 6 6 -1.</_>
+        <_>
+          0 13 6 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          0 14 5 6 -1.</_>
+        <_>
+          0 17 5 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 2 4 3 -1.</_>
+        <_>
+          2 3 4 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 3 5 12 -1.</_>
+        <_>
+          2 7 5 4 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          2 17 12 3 -1.</_>
+        <_>
+          2 18 12 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 1 3 3 -1.</_>
+        <_>
+          3 2 3 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 1 3 12 -1.</_>
+        <_>
+          3 7 3 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 2 2 3 -1.</_>
+        <_>
+          3 3 2 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          3 7 9 11 -1.</_>
+        <_>
+          6 7 3 11 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 0 12 8 -1.</_>
+        <_>
+          8 0 4 8 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          4 0 16 2 -1.</_>
+        <_>
+          4 0 8 1 2.</_>
+        <_>
+          12 1 8 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 1 6 5 -1.</_>
+        <_>
+          8 1 3 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 7 12 12 -1.</_>
+        <_>
+          11 7 6 12 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 9 3 2 -1.</_>
+        <_>
+          5 10 3 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 9 9 3 -1.</_>
+        <_>
+          8 10 3 1 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          5 10 10 5 -1.</_>
+        <_>
+          10 10 5 5 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          6 0 9 13 -1.</_>
+        <_>
+          9 0 3 13 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 6 15 -1.</_>
+        <_>
+          9 6 2 5 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 1 6 11 -1.</_>
+        <_>
+          9 1 2 11 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 3 4 10 -1.</_>
+        <_>
+          9 3 2 10 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          7 16 5 3 -1.</_>
+        <_>
+          7 17 5 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 0 4 6 -1.</_>
+        <_>
+          6 2 4 2 3.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 13 6 3 -1.</_>
+        <_>
+          8 14 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          8 16 6 3 -1.</_>
+        <_>
+          8 17 6 1 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          9 2 4 6 -1.</_>
+        <_>
+          11 2 2 6 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 0 6 14 -1.</_>
+        <_>
+          10 0 3 7 2.</_>
+        <_>
+          13 7 3 7 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          10 4 8 2 -1.</_>
+        <_>
+          10 4 8 1 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 0 2 3 -1.</_>
+        <_>
+          12 0 1 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          11 1 9 6 -1.</_>
+        <_>
+          14 3 3 2 9.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 1 7 6 -1.</_>
+        <_>
+          13 3 7 2 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 3 6 6 -1.</_>
+        <_>
+          13 6 6 3 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          13 5 6 11 -1.</_>
+        <_>
+          16 5 3 11 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          14 3 4 16 -1.</_>
+        <_>
+          14 7 4 8 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 0 4 4 -1.</_>
+        <_>
+          15 1 4 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 1 3 4 -1.</_>
+        <_>
+          15 2 3 2 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 2 4 15 -1.</_>
+        <_>
+          15 7 4 5 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          15 5 5 9 -1.</_>
+        <_>
+          15 8 5 3 3.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 0 4 1 -1.</_>
+        <_>
+          18 0 2 1 2.</_></rects>
+      <tilted>0</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 2 4 4 -1.</_>
+        <_>
+          16 2 4 2 2.</_></rects>
+      <tilted>1</tilted></_>
+    <_>
+      <rects>
+        <_>
+          16 18 4 2 -1.</_>
+        <_>
+          18 18 2 2 2.</_></rects>
+      <tilted>0</tilted></_></features></cascade>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/params.xml

@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<params>
+  <stageType>BOOST</stageType>
+  <featureType>HAAR</featureType>
+  <height>20</height>
+  <width>20</width>
+  <stageParams>
+    <boostType>GAB</boostType>
+    <minHitRate>9.9500000476837158e-01</minHitRate>
+    <maxFalseAlarm>5.0000000000000000e-01</maxFalseAlarm>
+    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
+    <maxDepth>1</maxDepth>
+    <maxWeakCount>100</maxWeakCount></stageParams>
+  <featureParams>
+    <maxCatCount>0</maxCatCount>
+    <featSize>1</featSize>
+    <mode>ALL</mode></featureParams></params>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage0.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage0>
+  <maxWeakCount>2</maxWeakCount>
+  <stageThreshold>-1.5131105482578278e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 38344 7.3132544755935669e-02</internalNodes>
+      <leafValues>
+        -9.6969699859619141e-01 8.7999999523162842e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 56105 3.7634912878274918e-02</internalNodes>
+      <leafValues>
+        -9.7909134626388550e-01 8.1838589906692505e-01</leafValues></_></weakClassifiers></stage0>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage1.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage1>
+  <maxWeakCount>3</maxWeakCount>
+  <stageThreshold>-9.9654263257980347e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 3548 2.1198132634162903e-01</internalNodes>
+      <leafValues>
+        -9.3999999761581421e-01 8.3333331346511841e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 72500 -5.1079854369163513e-02</internalNodes>
+      <leafValues>
+        7.5422900915145874e-01 -8.4309655427932739e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 116744 3.2548047602176666e-02</internalNodes>
+      <leafValues>
+        -8.1077164411544800e-01 8.0424255132675171e-01</leafValues></_></weakClassifiers></stage1>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage10.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage10>
+  <maxWeakCount>4</maxWeakCount>
+  <stageThreshold>-6.8541038036346436e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 81542 -2.0627105608582497e-02</internalNodes>
+      <leafValues>
+        6.0606062412261963e-02 -8.3516484498977661e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 52609 9.9415913224220276e-02</internalNodes>
+      <leafValues>
+        -6.4717310667037964e-01 5.1321762800216675e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 106510 -2.8571443632245064e-02</internalNodes>
+      <leafValues>
+        3.8076385855674744e-01 -7.0071691274642944e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 94 1.7725368961691856e-02</internalNodes>
+      <leafValues>
+        -4.7960722446441650e-01 6.6265738010406494e-01</leafValues></_></weakClassifiers></stage10>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage11.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage11>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-1.3034328222274780e+00</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 30719 -6.2260786071419716e-03</internalNodes>
+      <leafValues>
+        1.5384615957736969e-01 -7.9591834545135498e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 119263 -4.6867121011018753e-02</internalNodes>
+      <leafValues>
+        3.6055722832679749e-01 -5.8249193429946899e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 118529 -1.9795228727161884e-03</internalNodes>
+      <leafValues>
+        5.0797051191329956e-01 -5.0618976354598999e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 48288 3.5088375210762024e-02</internalNodes>
+      <leafValues>
+        -7.3651200532913208e-01 4.1671240329742432e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 53416 1.5235868049785495e-03</internalNodes>
+      <leafValues>
+        3.0445036292076111e-01 -8.4970545768737793e-01</leafValues></_></weakClassifiers></stage11>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage12.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage12>
+  <maxWeakCount>4</maxWeakCount>
+  <stageThreshold>-6.6577988862991333e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 79372 -2.0102638751268387e-02</internalNodes>
+      <leafValues>
+        7.1428573131561279e-01 -7.1806168556213379e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 112022 6.5985828638076782e-02</internalNodes>
+      <leafValues>
+        -7.8912955522537231e-01 2.9239723086357117e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 30719 -1.4360356144607067e-03</internalNodes>
+      <leafValues>
+        3.3544215559959412e-01 -7.7690732479095459e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 53422 3.7629939615726471e-02</internalNodes>
+      <leafValues>
+        -5.7326024770736694e-01 5.3679192066192627e-01</leafValues></_></weakClassifiers></stage12>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage13.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage13>
+  <maxWeakCount>5</maxWeakCount>
+  <stageThreshold>-7.6405721902847290e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 28796 -1.8220141530036926e-02</internalNodes>
+      <leafValues>
+        1. -6.8510639667510986e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 71910 -1.2162408791482449e-02</internalNodes>
+      <leafValues>
+        6.5581905841827393e-01 -5.0600630044937134e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 93726 -4.4847460230812430e-04</internalNodes>
+      <leafValues>
+        3.7500736117362976e-01 -8.8655352592468262e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 38598 6.7975055426359177e-03</internalNodes>
+      <leafValues>
+        -4.7455802559852600e-01 6.2044888734817505e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 89951 8.3894869312644005e-03</internalNodes>
+      <leafValues>
+        -4.6866527199745178e-01 7.1337395906448364e-01</leafValues></_></weakClassifiers></stage13>
+</opencv_storage>

vinniesniper-54816/task1/_lab/007-train-beach-test2/xml_step2_t3/stage2.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<opencv_storage>
+<stage2>
+  <maxWeakCount>3</maxWeakCount>
+  <stageThreshold>-8.4922987222671509e-01</stageThreshold>
+  <weakClassifiers>
+    <_>
+      <internalNodes>
+        0 -1 107351 6.5322615206241608e-02</internalNodes>
+      <leafValues>
+        -8.7939697504043579e-01 5.5102038383483887e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 3688 1.9205823540687561e-01</internalNodes>
+      <leafValues>
+        -7.1354663372039795e-01 7.1951913833618164e-01</leafValues></_>
+    <_>
+      <internalNodes>
+        0 -1 94600 -1.0098288208246231e-01</internalNodes>
+      <leafValues>
+        7.4371367692947388e-01 -6.5768426656723022e-01</leafValues></_></weakClassifiers></stage2>
+</opencv_storage>