xthan/VITON

problem with doing inference on new pictures

Iman-Johary opened this issue · 3 comments

Iman-Johary commented

I am trying to inference on pictures beside the pictures that is on dataset right now. the problem is that the human parsing segmentation that is used in dataset have 14 classes but the lip dataset and github repository that you introduced for human parsing have 20 classes.
anyone knows, in dataset, which network is used for human parsing segmentation?

xthan commented

https://github.com/Engineering-Course/LIP_SSL is used but you can also use https://github.com/Engineering-Course/CIHP_PGN which gives better results. For which classes are used please refer to https://github.com/xthan/VITON/blob/master/utils.py#L56. Other classes are simply ignored.

greykoalacode commented

@xthan Hello,
Can you share clear steps to run this project locally ?
Thanks.

  • 👍1
nikhilchame03 commented

hey I started doing this project but..am facing lot of problems is there someone if someone is willing to help me please contact me nikhilchame03@gmail.com insta:-nikhil_chame