CFLD

CFLD copied to clipboard

johndpope

In your paper, Perception-Refined Decoder uses source image encoder. So, I thought appearance encoder should be used, but in your code you use 'down_block_additional_residuals' which uses pose encoder. Why is...

justinday123

Is pose map(keypoint coordinate) must needed? I want to inference with my own dataset for pose. def build_pose_img(annotation_file, img_path): string = annotation_file.loc[os.path.basename(img_path)] array = load_pose_cords_from_strings(string['keypoints_y'], string['keypoints_x']) pose_map = torch.tensor(cords_to_map(array, (256,...

justinday123

 Hello authors, thanks for the great work. I want to know how you obtained the results in Table 2, which seem to differ from those provided in the original...

CHNxindong

100%|███████████████████████████████████████████████████████████████████████████████████████████| 233M/233M [00:16

kiko175457

Could the model checkpoints for the market1501 dataset be published, or could the relevant experimental details be elaborated

2

Thank you very much for reading my question. I am currently working on person reid generation and I am very interested in your work. I want to try using your...

zhi-time

 May I ask how this problem should be solved?

sirilier

I may have a question: What resolution is the market-1501 dataset trained on? whether it's 128x64 following other methods? If so, low resolution images( like 128x64) input to SD can...

Samuel-Recovery-123

Thank you for your work! When I run your playground.ipynb file with modifying the img_from to my custom image, the identity of the generated image is not same as my...

manhtoanbui01