A strange problem encountered during training about espnetv2 HOT 15 CLOSED

Did you process Cityscapes dataset correctly? Seems like an issue with labels.

from espnetv2.

Yes,I did ! 255 converted to 19 !

from espnetv2.

After 6 epoch!

from espnetv2.

I mean Cityscapes labels are not continuous between 0 and 19. You need to first convert them to continuous values. Have you done this?

from espnetv2.

Yes ，i have used this code https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/preparation/createTrainIdLabelImgs.py to conver them!

from espnetv2.

Could you just cross verify label images for the validation set are correct?

Which PyTorch version are you using?

from espnetv2.

could you please also check if this observation is the same if you use training set as your validation set?

from espnetv2.

Pytorch version 1.0.1 post2, i will try you methods ! thanks

from espnetv2.

This observation is the same if I use training set as my validation set
and my validation set is correct ,Throughout the code, I only changed the two loss values needed for training to only one loss value.

from espnetv2.

Could you point me to your repo?

from espnetv2.

output1, output2 = model(input) #set the grad to zero optimizer.zero_grad() loss1 = criterion(output1, target) loss2 = criterion(output2, target) loss = loss1 + loss2

change to

output1=model(input) optimizer.zero_grad() loss=criterion(output1, target)
No change in other places
sorry ,I didn't create a repo

from espnetv2.

Well you need to change the model file too, so that you get only one output instead of two.

from espnetv2.

I used the EESP module in your code to redesign the network structure and only have one output, then modify the training code to what I told you, the other parts have not changed, the data set is no problem, you also see the network can Training, but there was a problem with the verification, but when I used this code to train other network structures, everything was fine! I don't know what caused it.

from espnetv2.

Could you use the original code (without your changes) and see if it works?

If that works, then try incorporating your changes one by one. This will help you to debug the error.

from espnetv2.

Thanks ,I will do it!

from espnetv2.