search

Luodian / RelateAnything

Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
Apache License 2.0
438 stars 20 forks source link

Is the demo on the HuggingFace website using CPU or GPU to inference? #2

Closed xiaozhuka closed 1 year ago

xiaozhuka commented 1 year ago

Is the demo on the HuggingFace website using CPU or GPU to inference?

Testing with sample data is a little too slow. It took bout 500s to show the result.

What about the demo on Gradio, it's better. About 10s.

Jingkang50 commented 1 year ago

Thank you for your interest in the project! Actually we don't have budget to get GPU support from huggingface so we can only use CPU there, but the gradio demo is built on our own server with GPU.