pytorch-semseg icon indicating copy to clipboard operation
pytorch-semseg copied to clipboard

pspnet training

Open kingloo2014 opened this issue 4 years ago • 2 comments

hello, when I trained the pspnet, I found the ouput of this network has 2 tensors. So, the loss function cannot accept this output and lead to crash. Could you tell me which loss function should be used in this network ?

kingloo2014 avatar May 20 '20 09:05 kingloo2014

When training, there are two loss functions, only one in the test phase.

yyyjia avatar Jul 02 '20 15:07 yyyjia

hello, when I trained the pspnet, I found the ouput of this network has 2 tensors. So, the loss function cannot accept this output and lead to crash. Could you tell me which loss function should be used in this network ?

When using PSPNet, it seems that you should use "multi_scale_cross_entropy" instead of "cross_entropy" in your config file.

Da-He avatar Oct 01 '20 08:10 Da-He