Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

GPU Acceleration to increase performance #377

Closed
milind-yadav opened this issue Nov 3, 2023 · 1 comment · Fixed by #545
Closed

GPU Acceleration to increase performance #377

milind-yadav opened this issue Nov 3, 2023 · 1 comment · Fixed by #545
Labels
question Further information is requested

Comments

@milind-yadav
Copy link

Do we have any option to use GPU to increase performance of model loading and detection?
As currently in Object Detection it's taking around 10 seconds. If we want to do this on GPU, can we do that?

Running below lines through web worker, increases overall UI experience but not increases any performance.

const model = await pipeline("object-detection", "Xenova/detr-resnet-50");
const result = await model(img, { threshold: 0.9 });

Can we use GPU for that?

@milind-yadav milind-yadav added the question Further information is requested label Nov 3, 2023
@felladrin
Copy link
Contributor

We can't use GPU yet, but keep an eye on this other issue, which relates to the progress of WebGPU support:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants