search

clcarwin / sphereface_pytorch

A PyTorch Implementation of SphereFace.
MIT License
714 stars 172 forks source link

stuck during training #30

Closed fluctlux closed 6 years ago

fluctlux commented 6 years ago

Thanks for you codes.It really helpful. I use cleaned CASIA-WebFace, and have 455594 photos.After one epoch train,it stuck at 04:26:07 Te=0 Loss=8.7917 | AccT=2.0000% (12200/454469) 8.2977 16.70 888

when i use interrupt ,the program stop at '' File "train.py", line 142, in train(epoch,args) File "train.py", line 103, in train img,label = ds.get() File "/sphereface/dataset.py", line 113, in get index,imageshape,labelshape,pathlist = self.result.get()''

By the way,it always remain ''raise BadZipFile("Bad magic number for file header")zipfile.BadZipFile: Bad magic number for file header'' and ''zipfile.BadZipFile: File name in directory 'CASIA-WebFace/1813440/030.jpg' and header b'CASIA-WebFace/0110168/158.jpg' differ.'' is there something wrong? How to solve this issue?Thank you.

zhao181 commented 6 years ago

How did you solve this problem? My training procedure also raise BadZipFile

fluctlux commented 6 years ago

My problem solved since I change Python3.5 to Python2.7