minar09 / cp-vton-plus

Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020
https://minar09.github.io/cpvtonplus/
MIT License
346 stars 120 forks source link

CIHP_PGN model unusable due to Python 2.7 depreciation #53

Closed pra17dod closed 3 years ago

pra17dod commented 3 years ago

While custom image testing, the CIHP_PGN model for the image-parse is not working after the depreciation of the Python 2.7. Could you please suggest any other model for the same or any workaround for working implementation in Python 3 other than default python 2 to 3 converters?

minar09 commented 3 years ago

Hi, I have a working CIHP_PGN repository in python 3, you could check if you like to: https://github.com/minar09/PGN_tf . However, I think you can use CIHP_PGN (https://github.com/Engineering-Course/CIHP_PGN) or Graphonomy (https://github.com/Gaoyiminggithub/Graphonomy) either of the models for generating segmentation, and their official codebase should be or work in python 3 AFAIK.

pra17dod commented 3 years ago

I am very grateful for your reply, your work on PGN_tf really helped.