fc4-pytorch
fc4-pytorch copied to clipboard
A PyTorch implementation of FC4: Fully Convolutional Color Constancy with Confidence-weighted Pooling
Results
3
fc4-pytorch issues
Sort by
recently updated
recently updated
newest added
How to input own pictures for testing
(After downloading the data, please extract it and move the images and coordinates folders and the folds.mat file to the dataset folder.) I can't understand this sentence. I have downloaded...
the loss defined for training only is angle loss. there is no any other constraint for mask, this is efficient for confidence. I run some raw image with cwp file...