pytorch-multi-label-classifier icon indicating copy to clipboard operation
pytorch-multi-label-classifier copied to clipboard

Published 20 hours ago • verified publisher icon pangwong

the batch normalization layer of resnet output NaN

Open Ereebay opened this issue 6 years ago • 0 comments

I tried the resnet50 layer as the classification model, and I changed the input size of the image, but the loss of validation step was nan. I found the problem was the batch normalization layer, the output of it was NaN. Do you have any idea about it?

Ereebay avatar Jul 08 '19 07:07 Ereebay