-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Model 1 results for warping is unexpected #4
Comments
Could you give me more information?
Also, I'm not sure about the extrapolation performance of VITON-GAN. The dataset I used only contains female models. |
Hi @shionhonda @pratiklodha95 I got the same results. Even on the original test files, using the provided GMM epoch 99 file. Thoughts? |
Thanks for reporting @jakubLangr . I might have provided different GMM model file. Let me check. |
I did reproduce the successful result by 1) cloning this repository, 2) downloading the dataset and the trained model |
Hi @shionhonda I went ahead and trained your algorithm from scratch. These are the results from my training run over the weekend. The images seem within norms so it seems that the training code for GMM is working on my machine. However, I am fairly confident that the pretrained I do agree with your suggestion that it is likely that TPS is not working, but I am not sure why. I am now re-running it on the freshly re-trained model. Out of curiosity, what setup are you using (Pytorch / Cuda versions?) & OS? |
@jakubLangr
Necks are removed in LIP. |
I implemented the code as mention in this repo and cp-vton repo.
Everything is working fine, but the model results from the part 1 model is not as expected,
Would like to if there is a specific formats of input one has to give, I have kept all inputs as per your code and data preparation code from cp-vton repo.
for simple inputs like
![image](https://user-images.githubusercontent.com/6401006/66098858-f1d18600-e5c1-11e9-8521-96b46f942af9.png)
image
and
![image](https://user-images.githubusercontent.com/6401006/66098862-f7c76700-e5c1-11e9-8393-23de13cb3f7f.png)
image
The text was updated successfully, but these errors were encountered: