Giters

levindabhi / SieveNet

This is the unofficial implementation of SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About the output of inference.py

lyx0208 opened this issue · comments

commented

I try to test the try-on result with the inference.py according to the steps in the readme file:

  1. download the checkpoints
  2. download the caffe models
  3. get the human parsing
  4. put the photos into different paths
  5. run inference

But the try-on output I get is rather poor than the figures in the paper: the margin is blurry and there's some white part at the margin. So is there anything wrong when I use your code?

commented

Steps you mentioned is correct for inferencing image. I tried to match with paper details but I am also not satisfied with results I am getting on test data. There can be few reasons but I am not aware of the real cause.