Getting bad segmentation results in output folder even after running test_pgn.py

[farazkhanfk7]

I downloaded the pretrained checkpoints and stored them inside checkpoints folder. After which I ran the test_pgn.py file and it created an output folder with two subfolders cihp_edge_maps and cihp_parsing_maps. Below is the output 0002190_vis.png which was created inside cihp_parsing_maps. And this is clearly not the output I was expecting.

What went wrong ? What have I missed ?
I have completed all these steps which were mentioned in Readme file.

• Download the pre-trained model and store in $HOME/checkpoint.
• Prepare the images and store in $HOME/datasets.
• Run test_pgn.py.
• The results are saved in $HOME/output

[TidamCo]

I just ran into the same problem I think. If you read the code, you'll see this :
RESTORE_FROM = './checkpoint/CIHP_pgn'
Which mean you have to unzip the pre-trained model and move the whole folder into checkpoint instead of just the content of the folder.

I find it really surprising that it didn't throw an error when I ran it with the checkpoints in the wrong place.

[sanazsab]

I just ran into the same problem I think. If you read the code, you'll see this : RESTORE_FROM = './checkpoint/CIHP_pgn' Which mean you have to unzip the pre-trained model and move the whole folder into checkpoint instead of just the content of the folder.

I find it really surprising that it didn't throw an error when I ran it with the checkpoints in the wrong place.

Many Thanks for your point. It also works for me.