895318

I might have figured out where the issue is. It could be due to a mismatch between my mean and stride values. Thank you very much.

> > > > 10000 is the number of iterations，not epochs! May I ask where to set epoch in the code?

请问这个问题你解决了吗？我把这个模块加进我的模型以后，一开始在双卡上回报这个错误，但移到单卡上也会发生这个问题。但奇怪的是相同的batch-size有时候就可以畅通无阻的训练，有的时候就会出现这个错误。 Traceback (most recent call last): File "train.py", line 33, in do_train( File "/root/autodl-tmp/PART-master/processor/processor.py", line 102, in do_train cls_g, cls_1 = model(img, target,mode='train') #0515 File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl...