数据集下载
wider face数据集下载链接: http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/
keras Faster RCNN训练源码
https://github.com/jiaka/faster_rcnn_keras_wider_face.git
将label改为VOC格式
解压下载好的label文件:wider_face_split,找到wider_face_train_bbx_gt.txt文件,打开发现label的形式是
0–Parade/0_Parade_marchingband_1_799.jpg (图片路径)
21 (此图片中的面孔数量)
78 221 7 8 2 0 0 0 0 0 (第一个人脸标注框)
78 238 14 17 2 0 0 0 0 0 (第二个人脸标注框)
…
标注框:
x1, y1, w, h, blur, expression, illumination, invalid, occlusion, pose(左上点横坐标,左上点纵坐标,框的宽度,框的高度,框的模糊程度,…(其他的查看readme文件))
而VOC2012的数据集格式(非图像分割)如下:
将wider face的label转换为VOC2012格式的代码
from skimage import io
import shutil
import random
import os
import string
headstr = """\
<annotation>
<folder>VOC2007</folder>
<filename>%06d.jpg</filename>
<source>
<database>My Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
<flickrid>NULL</flickrid>
</source>
<owner>
<flickrid>NULL</flickrid>
<name>company</name>
</owner>
<size>
<width>%d</width>
<height>%d</height>
<depth>%d</depth>
</size>
<segmented>0</segmented>
"""
objstr = """\
<object>
<name>%s</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>%d</xmin>
<ymin>%d</ymin>
<xmax>%d</xmax>
<ymax>%d</ymax>
</bndbox>
</object>
"""
tailstr = '''\
</annotation>
'''
def all_path(filename):
return os.path.join('widerface', filename)
def writexml(idx, head, bbxes, tail):
filename = all_path("Annotations/%06d.xml" % (idx))
f = open(filename, "w")
f.write(head)
for bbx in bbxes:
f.write(objstr % ('face', bbx[0], bbx[1], bbx[0] + bbx[2], bbx[1] + bbx[3]))
f.write(tail)
f.close()
def clear_dir():
if shutil.os.path.exists(all_path('Annotations')):
shutil.rmtree(all_path('Annotations'))
if shutil.os.path.exists(all_path('ImageSets')):
shutil.rmtree(all_path('ImageSets'))
if shutil.os.path.exists(all_path('JPEGImages')):
shutil.rmtree(all_path('JPEGImages'))
shutil.os.mkdir(all_path('Annotations'))
shutil.os.makedirs(all_path('ImageSets/Main'))
shutil.os.mkdir(all_path('JPEGImages'))
def excute_datasets(idx, datatype):
f = open(all_path('ImageSets/Main/' + datatype + '.txt'), 'a')
f_bbx = open('wider_face_split/wider_face_' + datatype + '_bbx_gt.txt', 'r')
while True:
filename = f_bbx.readline().strip('\n')
print(filename)
if not filename:
break
im = io.imread('widerface/WIDER_' + datatype + '/images/' + filename)
head = headstr % (idx, im.shape[1], im.shape[0], im.shape[2])
nums = f_bbx.readline().strip('\n')
bbxes = []
for ind in range(int(nums)):
bbx_info = f_bbx.readline().strip(' \n').split(' ')
bbx = [int(bbx_info[i]) for i in range(len(bbx_info))]
if bbx[7] == 0:
bbxes.append(bbx)
writexml(idx, head, bbxes, tailstr)
shutil.copyfile('widerface/WIDER_' + datatype + '/images/' + filename, all_path('JPEGImages/%06d.jpg' % (idx)))
f.write('%06d\n' % (idx))
idx += 1
f.close()
f_bbx.close()
return idx
if __name__ == '__main__':
clear_dir()
idx = 1
idx = excute_datasets(idx, 'train')
附处理好的VOC2012格式的wider face数据集下载https://pan.baidu.com/s/1n1NKd0DCWTqhmDrVAMJfCw 提取码:q2dj
训练结果
由于只训练了30轮左右,预测结果还不是很好,挑出比较好的一张