search

sangyun884 / HR-VITON

Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022).
818 stars 172 forks source link

Not correct segmentation image #41

Open OliverVarnce opened 1 year ago

OliverVarnce commented 1 year ago

I have prepared segmentation image in CIHP_PGN but when I execute it in HR-VITON I have this error:

ValueError: operands could not be broadcast together with shapes (1024,768) (1024,768,3)

lujiazho commented 1 year ago

I guess it's because you didn't convert it to P mode

Image.open("./output/cihp_parsing_maps/00008_00_vis.png").convert('P')
OliverVarnce commented 1 year ago

Yes! You are right. I have already figured out this issue. Thanks for tips.

MosbehBarhoumi commented 1 year ago

@OliverVarnce @lujiazho Is there a way to run CIHP_PGN on Google Colab, considering that the original code is written in TensorFlow 1.x and I am encountering difficulties while trying to migrate it to TensorFlow 2.x? Are there any migrated code or ideas available to help solve this problem?