could not find body_binary_masking.py and dataset_neck_skin_correction.py

[xqyd]

trafficstars

Hi! Can someone tell me where to find body_binary_masking.py and dataset_neck_skin_correction.py? I want to try some custom images but could not find these two. Many thanks!!!

[minar09]

Hi @xqyd , I removed those files as people were getting confused and the full processed dataset is already provided. Also, for custom images, if you generate segmentation with CIHP_PGN or Graphonomy, you don't need the dataset_neck_skin_correction.py. CIHP_PGN or Graphonomy already generate segmentation with the neck skin label. And for binary-masking, you can utilize the code from my another repository: https://github.com/minar09/Clothing-Matching Hope these help! Good luck. Thanks.

[stereomatchingkiss]

Cannot find the neck skin label from Graphonomy. From inference.py, only 20 labels.

label_colours = [(0,0,0)
                , (128,0,0), (255,0,0), (0,85,0), (170,0,51), (255,85,0), (0,0,85), (0,119,221), (85,85,0), (0,85,85), (85,51,0), (52,86,128), (0,128,0)
                , (0,0,255), (51,170,221), (0,255,255), (85,255,170), (170,255,85), (255,255,0), (255,170,0)]

Do I miss something?

Edit : After I run the script, it do parse neck. With cmd python exp/inference/inference.py --loadmodel weights/inference.pth --img_path img/000004_0.jpg --output_path output_images --output_name result.jpg

[stereomatchingkiss]

After experiments, I find out the Graphonomy treat label 10(jumpsuit) as neck, since the model is training with 21 labels and treat label 20 as neck, I would convert label 10 of Graphonomy to label 20, hope it works this way