Training model on cuda #180
Description
I wrote my own dataset to load MNIST data, The images are getting loaded, but these 2D images (i.e only 1 channel), this causes problem in torch.nn.Conv2d which expects a 4D Tensor, I tried loadin the images as 3D Tensor (32X32X1), but it still doesn't work and gives size mis-match error, please help.
This is the class for dataset:
This is the model:
This is the code throwing error(I understand the code for training isnt complete, i was just testing if it runs or not, and it doesnt):
Even if I load my data as 1X32X32, I still get the mismatch error as follows:
If dataset is changed to:
the error now is:
