部分轉載：https://zhuanlan.zhihu.com/p/31836357

該資料集出自於香港中文大學，可應用於行為分析和行人檢測。包含了1063張行人圖片。

密碼：xkka

轉換資料格式程式碼：

# coding=UTF-8
import os
from PIL import Image
from os import listdir, getcwd

image_path = "/data/yolo3/scripts/VOCdevkit/VOC2007/JPEGImages"                          # 圖片存放路徑，路徑固定
# 我們的標籤格式的路徑
filelist = open("./annotations_CUHK/CUHK.txt"
 
, "r")   # 1,我們的標籤存放路徑
sets=[('train')]

lines = filelist.readlines()

# 將CUHK的x,y,w,h格式轉換成yolo的X,Y,W,H
def convert(size, box):
   dw = 1./size[0]
   dh = 1./size[1]
   x = box[0] + box[2]/2.0
y = box[1] + box[3]/2.0
w = box[2]
   h = box[3]
   x = x*dw
   w = w*dw
   y = y*dh
   h = h*dh
   return (x,y,w,h)

# 
 
獲取要查詢的圖片的w,h
def get_size(image_id):
   im = Image.open('./VOCdevkit/VOC2007/JPEGImages/%s'%(image_id))   # 2,源圖片存放路徑
size = im.size
   w = size[0]
   h = size[1]
   return (w,h)

# 在labels目錄下建立每個圖片的標籤txt文件
def text_create(name,bnd):
   full_path = "./VOCdevkit/VOC2007/labels/%s.txt"%(name)
   size = get_size(name + '.jpg'
 
)
   convert_size = convert(size, bnd)
   file = open(full_path, 'a')
   file.write('0 ' + str(convert_size[0]) + ' ' + str(convert_size[1]) + ' ' + str(convert_size[2]) + ' ' + str(convert_size[3]) )
   file.write('\n')

# 獲取資料夾下所有圖片的圖片名
def get_name(file_dir):
   list_file=[]
   for root, dirs, files in os.walk(file_dir):
      for file in files:
         # splitext()將路徑拆分為檔名+副檔名，例如os.path.splitext(“E:/lena.jpg”)將得到”E:/lena“+".jpg"
if os.path.splitext(file)[1] == '.jpg':
            list_file.append(os.path.join(root, file))
   return list_file

# 當前工作環境下的絕對路徑
wd = getcwd()

for image_set in sets:
   if not os.path.exists('/data/yolo3/scripts/VOCdevkit/VOC2007/labels'):
      os.makedirs('/data/yolo3/scripts/VOCdevkit/VOC2007/labels')                     # 生成的yolo3標籤存放路徑，路徑固定
image_names = get_name(image_path)
   list_file = open('2007_%s.txt'%(image_set), 'w')
   for image_name in image_names:
      list_file.write('%s\n'%(image_name))
   list_file.close()

for line in lines:
   str_names = line.split()
   str_name = str_names[0]
   b = line.split()[1:]
   bnd = (float(b[0]) ,float(b[1]) ,float(b[2]) ,float(b[3]))
   text_create(str_name, bnd)