1.数据集
下载好voc数据集,以2007为例,把数据集(VOCtrainval_06-Nov-2007和VOCtest_06-Nov-2007)都解压同一个文件夹里,记住解压后的图片是从000001.jpg-009963.jpd的。
在VOCdevkit/目录下 运行voc2yolo.py代码
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
# 这里就体现出来了咱们在1.2步骤的时候我说的尽量按照那个目录名进行操作的优势,
# 在这可以剩下很多去修改名称的精力
# sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[ ('2007', 'train'), ('2007', 'val'), ('2007', 'test')] # 我只用了VOC2007
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle",
"bus", "car", "cat", "chair", "cow",
"diningtable", "dog", "horse", "motorbike", "person",
"pottedplant", "sheep", "sofa", "train", "tvmonitor"]
#classes = ["face"] # 修改为自己的label
def convert(size, box):
dw = 1./(size[0])