contrastive-unpaired-translation

contrastive-unpaired-translation copied to clipboard

Hello, Great work! I would like to ask if CUT can handle multi-channel images? The RGB image can be regarded as a 3-channel image, but now I need to use...

LiangJunhao-THU

CPU memory leak + cuDNN error when using the GPU with preprocess None

3

Two issues I've been running into when attempting to perform inference with the test.py script: 1. When running with GPU, with no preprocessing (i.e. input shape is size of input...

connorlee77

Test the CUT model raised a problem

1

After I run: python test.py --dataroot ./datasets/grumpifycat --name grumpycat_CUT --CUT_mode CUT --phase train，an error ocurred, FileNotFoundError: [Errno 2] No such file or directory: './checkpoints/grumpycat_CUT/latest_net_G.pth'. I don't understand, because before this,...

Deerzh

MLP network

2

Hi! First of all, awesome paper. I was wondering what the purpose of passing the feature maps through the MLP is?

CasperDL2805

Cant I test B to A?

2

I did not find any documentation for testing the learned network for transferring from B to A. Is there a way of doing it?

luuckiest

Training with aligned dataset

1

I was trying to train with an aligned dataset. The default (unaligned training) works fine. However if I want to leverage the aligned feature of the set I get this...

krummrey

Anyone try to use this solution to train a style transfer model between comics?

1

Like convert naruto style to one piece style, is this possible to be done?

stereomatchingkiss

AttributeError: Can't pickle local object 'Visdom.setup_socket.<locals>.run_socket'

4

AttributeError: Can't pickle local object 'Visdom.setup_socket..run_socket'

c1a1o1

Multi-GPU Testing fails

5

I tried to use the flag "--gpu_ids 0,1" in the command "python test.py --dataroot ./datasets/mscoco17/ --name model-name --CUT_mode CUT --phase train --load_size 786 --crop_size 786 --num_test 20 --gpu_ids 0,1". With...

martinUB

Pretrained segmentation model on cityscapes?

3

sorry to bother, I wonder if you could please publish your pretrained segmentation model on cityscapes

haoren55555