Pytorch RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed. at /opt/conda/conda

[christopher-ell]

Thanks for your help ptrblck!

Been a bit busy (and frustrating) I am still having issues. I was looking at the below link:

[solved] Assertion `cur_target >= 0 && cur_target < n_classes' failed

Hi guys, I am trying to learn Pytorch by using it for the Titanic kaggle competition. I completed the intro CIFAR-10 tutorial and decided to try to build a simple fully connected neural net. The problem is that I keep running into this error: ‘Assertion `cur_target >= 0 && cur_target < n_classes’ failed.’. I think I am loading the data correctly (I tried to apply the Data Loading and Processing tutorial) and I believe I have correctly set up the neural net. Of course, there’s always the chance t…

That persons problem was that the last layer wasn’t outputting the number of categories, but mine is implementing the correct number of layers resnet34.fc = nn.Linear(num_ftrs, 12).

The line that it says is not working is the loss = criteria(output, target) and printing the output and target gives one 12 x batch_size for output and batch_size x 1 for target.

Thanks