RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long

nlp
1

when running following notebook on google Colab it works fine
https://colab.research.google.com/drive/1nZ5JCnModfGBtANK3TJZEcykhEcLPN_q?authuser=1#scrollTo=-5jscIM8R4Gv

but on my local pc but I am getting this error when I am running the training cell
RuntimeError: Expected tensor for argument #1 ‘indices’ to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)

Note: I have the same TensorFlow and PyTorch Version as in Colab

2

I cannot access your code. Can you post relevant sections of the code here and the code line where you get the error.

3

Thanks @ra_schoonhoven I found the solution. basically I was passing (input,labels,embedding) as IntTensor instead of LongTensor but when I passed (input,labels,embedding) as LongTensor it worked for me