puhuk

Train with different image size

3

Hi, Thanks for the great work! I'm trying to train with different image size and change relevant code (input size, input_nc for initializing FeatureRegression in class GMM. But the result...

Question with keypoint detection code

3

From below code, it outputs value of keypoints by (heatmap * grid).sum(dim=(2, 3)) Then I can get tensor with shape of (10, 2) (Here, 10 is the number of keypoints)...

device = 'cuda' if torch.cuda.is_available() else 'cpu' 위 코드 실행 시, device 가 ('cuda',) 로 출력되어, 이후 CNN().to(device) 등의 to(device) 실행 시 오류가 출력됩니다. (to() received an invalid combination of...

Description: To resolve warnings : `np` is deprecated Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description...

Description: Modify to all_gather takes `group` Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description and/or example...

Description: Modify all_reduce to take `group` Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description and/or example...

Fixes #1992 Description: Update engine.py to resolve #1992 Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description...

Description: Update horovod to take all_reduce with group Check list: - [ ] New tests are added (if a new feature is added) - [ ] New doc strings: description...

Hi, thanks for the great work. As I train with your code, it seems to output result with paired human and garment images as shown in the below image, while...

Hi, Thank you for the great work. Could you open training code. Thanks