facebookresearch / ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
Other
676 stars 61 forks source link

Segmentation Problem #5

Closed ngthanhtin closed 1 year ago

ngthanhtin commented 1 year ago

Hi @all, Thank you for your great work. When I run the demo.py as the following: python demo.py --input custom_images/*.JPEG --output output/ --class-name drum, trifle, person, punching bag, mouse, trap, volleyball, piano, boxer, plunger, harmonica, dog, muzzle, violin

The outputs were not as I expected:

Screenshot 2022-12-19 at 9 33 09 PM Screenshot 2022-12-19 at 9 33 01 PM

So do I have any mistake when running demo.py file? or I forgot the pretrained weight? If this is the problem, could you provide the pretrained weight file, it would be really kind of you.

Best, Tin