Thái Thanh Tuấn

Hi @TamerElsherif , can you debug by printing something to make sure that the GMM load the checkpoints correctly? It looks like it is not loaded. Regards.

If you check the networks.py. You can see the implementation of this loss.  In this, you can use DT or DT2 and we have already define DT and DT2...

> why use l1_loss(warped_cloth,c),different from paper said(warped_mask,cm)? Oh, You are right, I fixed it. This is a mistake uploading the wrong version of the code. Thank you very much for...

> should the l1_loss be (warped_mask, pcm) instead of (warped_mask, cm)? Oh no, my mistake again. :(. You are right SaraH20. it should be pcm to be the same as...

This code is just heuristic. For more accuracy, you need to build a network for generating the mask. But for ease, you can simply change the thresholds to a lower...

Please refer to other issues for more information: https://github.com/minar09/cp-vton-plus/issues/9 And this: https://github.com/minar09/cp-vton-plus/issues/8 Somebody has the same problem and comes from a different OS return "listDir" function. -------------  Yes, In...

https://github.com/minar09/cp-vton-plus/issues/24#issuecomment-689321590 You can check this closed issue for more information.

First, It is possible. Some people have already done it from other issues. Second, Sorry that at this time, we don't have time to make it. Regards

@shufangxun I think your question is about the number of 40, This is hyperparameter and we got this through some trainings. At first, we tried with loss = Lwarp +...

You can find new segmentation (after neck correction) and pretrained model here. https://drive.google.com/drive/folders/1fol0mMvrgjGE5lZlqR7y-7LhOOraU1wQ?usp=sharing