harshithabk

How to avoid blocky reconstruction

4

@pathak22 How to remove the blocking artifact in the patch loction after reconstruction of image? What value to be set in this part of code? image_ctx[{{},{1},{1 + opt.fineSize/4 + opt.overlapPred,...

Regarding image rescaling

1

@pathak22 : As per our observation, the models rescales the images to 128x128. Since our input image resolution is HD, we expect the reconstructed output also to be of same...

Hi, By referring the below link: https://github.com/leehomyc/Faster-High-Res-Neural-Inpainting/issues/24 I trained train.lua with human face data in context encoder https://github.com/pathak22/context-encoder The trained model, when tested, executes in context encoder. However the same...

Hi Neil, I have couple of queries regarding the training data. I understand that the training set should be of dimensions 128x384. However in train.py, the input given for training...