INRIAPerson数据集转化为yolo训练格式并可视化
记录贴：将inria行人检测数据集转化为YOLO可以训练的txt格式
inria行人检测数据集解压后有train和test文件，将里面的标注信息提取出来
转化代码
# coding=UTF-8
import os
import re
from PIL import Image
sets=['train']
#需要填写变量image_path、annotations_path、full_path
image_path = r"D:\BaiduNetdiskDownload\59_INRIA Person Dataset\shuju1/" # 图片存放路径，路径固定
annotations_path = r"D:\BaiduNetdiskDownload\59_INRIA Person Dataset\INRIAPerson\Test\annotations/" #文件夹目录 # INRIA标签存放路径
annotations= os.listdir(annotations_path) #得到文件夹下的所有文件名称
# 获取文件夹下所有图片的图片名
def get_name(file_dir):
list_file=[]
for root, dirs, files in os.walk(file_dir):
for file in files:
# splitext()将路径拆分为文件名+扩展名，例如os.path.splitext(“E:/lena.jpg”)将得到”E:/lena“+".jpg"
if os.path.splitext(file)[1] == '.jpg':
list_file.append(os.path.join(root, file))
return list_file
# 在labels目录下创建每个图片的标签txt文档
def text_create(name,bnd):
full_path = r"D:\BaiduNetdiskDownload\59_INRIA Person Dataset\labels1/%s.txt"%(name)
size = get_size(name + '.png')
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')
# 获取要查询的图片的w,h
def get_size(image_id):
im = Image.open(r'D:\BaiduNetdiskDownload\59_INRIA Person Dataset\INRIAPerson\Test\pos/%s'%(image_id)) # 源图片存放路径
size = im.size
w = size[0]
h = size[1]
return (w,h)
# 将Tagphoto的x,y,w,h格式转换成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] - box[0]
h = box[3] - box[1]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x,y,w,h)
# 将处理的图片路径放入一个ｔｘｔ文件夹中
for image_set in sets:
if not os.path.exists(r'D:\BaiduNetdiskDownload\59_INRIA Person Dataset\labels1'):
os.makedirs(r'D:\BaiduNetdiskDownload\59_INRIA Person Dataset\labels1') # 生成的yolo3标签存放路径，路径固定
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()
s = []
for file in annotations: #遍历文件夹
str_name = file.replace('.txt', '')
if not os.path.isdir(file): #判断是否是文件夹，不是文件夹才打开
with open(annotations_path+"/"+file) as f : #打开文件
iter_f = iter(f); #创建迭代器
for line in iter_f: #遍历文件，一行行遍历，读取文本
str_XY = "(Xmax, Ymax)"
if str_XY in line:
strlist = line.split(str_XY)
strlist1 = "".join(strlist[1:]) # 把list转为str
strlist1 = strlist1.replace(':', '')
strlist1 = strlist1.replace('-', '')
strlist1 = strlist1.replace('(', '')
strlist1 = strlist1.replace(')', '')
strlist1 = strlist1.replace(',', '')
b = strlist1.split()
bnd = (float(b[0]) ,float(b[1]) ,float(b[2]) ,float(b[3]))
text_create(str_name, bnd)
else:
continue
可视化一下
判断转化是否正确，写了一个可视化代码
import os
import cv2
img_path = r'D:\BaiduNetdiskDownload\59_INRIA Person Dataset\INRIAPerson\Train\pos/'
label_path = r'D:\BaiduNetdiskDownload\59_INRIA Person Dataset\labels/'
f = os.listdir(img_path)
def paint(label_file, img_file):
#读取照片
img = cv2.imread(img_file)
img_h, img_w, _ = img.shape
with open(label_file, 'r') as f:
obj_lines = [l.strip() for l in f.readlines()]
for obj_line in obj_lines:
cls, cx, cy, nw, nh = [float(item) for item in obj_line.split(' ')]
color = (0, 0, 255) if cls == 0.0 else (0, 255, 0)
x_min = int((cx - (nw / 2.0)) * img_w)
y_min = int((cy - (nh / 2.0)) * img_h)
x_max = int((cx + (nw / 2.0)) * img_w)
y_max = int((cy + (nh / 2.0)) * img_h)
cv2.rectangle(img, (x_min, y_min), (x_max, y_max), color, 2)
cv2.imshow('Ima', img)
cv2.waitKey(0)
for i in f:
label_path_name = label_path + i.replace('png','txt')
img_path_name = img_path + i
print(label_path_name)
print(img_path_name)
paint(label_path_name,img_path_name)
发现这个数据集的多人场景下只标注了几个人