About the output of inference.py
lyx0208 opened this issue · comments
Yixuan Li commented
I try to test the try-on result with the inference.py according to the steps in the readme file:
- download the checkpoints
- download the caffe models
- get the human parsing
- put the photos into different paths
- 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?
Levin Dabhi 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.