Reconstructing an image after using extract_image_patches

Question

I have an autoencoder that takes an image as an input and produces a new image as an output.

The input image (1x1024x1024x3) is split into patches (1024x32x32x3) bef

Answer 1

Tf 2.0 users can use space_to_depth and depth_to_space if you aren't doing overlapping blocks.