Matiur Rahman Minar

Hi @hamzanaeem1999 , to run on custom images, you need to prepare the masks and segmentation files from the input images, according to the dataset used here. You can also...

Added now. Please check. Thanks.

Hi @hematank, sorry to say that I only used this repository for testing purpose. Please refer to the original repo (https://github.com/switchablenorms/DeepFashion_Try_On) for training. Thank you.

Hi, I think I already made that change not to dress clothes randomly. Currently, it dresses clothes according to the image pairs from the list files e.g. test_pairs.txt. You can...

Hi @hrushikesh26 , I have used this repository only for testing the VITON dataset. I guess, the way the repository is made, it's a bit long procedure to apply for...

Hi, @1702609 , thanks for your post. However, I am sorry to let you know that I have only tested and modified the testing script. The training scripting was copied...

Thanks for pointing out.

@hjkim811 , if it seems complicated, I guess you can just put the data inside the same folder as the script for the testing purpose and try running.

It might be related to your work environment, I think you may find solutions online. For instance: https://stackoverflow.com/questions/51691563/cuda-runtime-error-59-device-side-assert-triggered

Can you please clarify more details on your issue? Do you mean you have a mismatch with the number of labels or something else? CIHP_PGN generated segmentation labels number should...