RuntimeError: view size is not compatible with input tensor's size and stride

[aaliixii]

Hi,
When I try and run this with my own dataset with 4 classes, I get this error.

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Any idea what could be causing this?

[mohekouzhuxiangyu]

hi, have you resolved this problem? i meet the same proble

[AvisP]

Hi,

I resolved it by changing the following line

PyTorch-Pretrained-ViT/examples/imagenet/main.py

Line 419 in 8ec2cab

correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)

to correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)