search

OFA-Sys / DAFlow

124 stars 16 forks source link

Hello, what is your input for generating mask #7

Closed zbq777sc closed 1 year ago

zbq777sc commented 1 year ago

I want to run your code: data/data_process/get_img_agnostic.py

But I found that I didn't know what input it needed

Can you tell me, thank you!

ShuaiBai623 commented 1 year ago

the input is the datapath and the filenames list. The datapath consists of the pose_keypoints, original clothes images, model images and human-parsing results, which are from CPVTON-plus. Unzip the viton_plus.zip from CPVTON-plus.

tengolagan commented 1 year ago

Hi, please can you tell me how you get the human-parsing results (json files?) ? thanks!!

tudragon154203 commented 1 year ago

the input is the datapath and the filenames list. The datapath consists of the pose_keypoints, original clothes images, model images and human-parsing results, which are from CPVTON-plus. Unzip the viton_plus.zip from CPVTON-plus.

I think the paper is about running a virtual trying without relying on extra stages like human-parsing. So we do still need the parsing in order to generate img agnostic, don't we?