Patch a full dataset folder images

vision
1

How can I create patches of size (64,64) for images with 3 channels and save them from a dataset of size (256,256).

2

You could use tensor.unfold to create the patches and save them via torch.save.

3

How tensor.unfold perform patching, is it randomaly?
And then how can I reconstruct the original images?

4

No, it’s not randomly and the example in the docs would show how the kernel size and stride is applied.
To reconstruct the input, you could take a look at the nn.Unfold and nn.Fold docs.