MTCNN-Tensorflow icon indicating copy to clipboard operation
MTCNN-Tensorflow copied to clipboard

Why you use "replace=True" in gen_imglist_pnet.py ?

Open creatist opened this issue 6 years ago • 2 comments

There is a statement for choose negative examples “neg_keep = npr.choice(len(neg), size=len(neg), replace=True)” in gen_imglist_pnet.py. The augment "replace=True" will lead to repetitive examples, so why not use "replace=False" to get more effective examples?

creatist avatar Nov 17 '18 02:11 creatist

Agree with @creatist , same doubt on this line.

qlibp avatar Nov 18 '18 04:11 qlibp

agree

JianyuanYin avatar May 29 '20 05:05 JianyuanYin