jogisuda
Results
3
comments of
jogisuda
Facing exactly the same issue here
Found the solution. My problem was the size of the images: I had batches of dimension (16, 3, 32, 32) (16 images per batch, 3 channels, 32 height/width). Got it...
Thank you! It looks like creating a tensor makes torch detach the old tensors and hence lose the gradient information. stacking was the appropriate choice.