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

Added Segment Anything interactor for GPU/CPU #6008

Merged
merged 7 commits into from
Apr 12, 2023
Merged

Conversation

bsekachev
Copy link
Member

@bsekachev bsekachev commented Apr 11, 2023

Motivation and context

Idea of the PR is to finish this one #5990
Deploy for GPU: ./deploy_gpu.sh pytorch/facebookresearch/sam/nuclio/
Deploy for CPU: ./deploy_cpu.sh pytorch/facebookresearch/sam/nuclio/

If you want to use GPU, be sure you setup docker for this guide.

How has this been tested?

Manual testing
demo2

Resolved issue #5984
But the interface probably can be improved

Checklist

  • I submit my changes into the develop branch
  • I have added a description of my changes into the CHANGELOG file
  • I have updated the documentation accordingly
  • I have added tests to cover my changes
  • I have linked related issues (see GitHub docs)
  • I have increased versions of npm packages if it is necessary
    (cvat-canvas,
    cvat-core,
    cvat-data and
    cvat-ui)

License

  • I submit my code changes under the same MIT License that covers the project.
    Feel free to contact the maintainers if that's a concern.

@bsekachev bsekachev changed the title Finished Segment Anything interactor for GPU Finished Segment Anything interactor for GPU/CPU Apr 11, 2023
@bsekachev bsekachev requested a review from mdacoca as a code owner April 11, 2023 18:43
@bsekachev bsekachev changed the title Finished Segment Anything interactor for GPU/CPU Added Segment Anything interactor for GPU/CPU Apr 11, 2023
@nmanovic
Copy link
Contributor

@bsekachev , need to add information into README.md as well.

@nmanovic nmanovic merged commit 9cbd510 into develop Apr 12, 2023
@nmanovic nmanovic deleted the bs/sam_deploy_gpu branch April 12, 2023 08:11
@medphisiker
Copy link

Thank you very much for integrating this neural network! Works like fBRs, but much more accurate. It's great that it has an inference on both CPU and GPU.

mikhail-treskin pushed a commit to retailnext/cvat that referenced this pull request Jul 1, 2023
Idea of the PR is to finish this one cvat-ai#5990
Deploy for GPU: ``./deploy_gpu.sh pytorch/facebookresearch/sam/nuclio/``
Deploy for CPU: ``./deploy_cpu.sh pytorch/facebookresearch/sam/nuclio/``


If you want to use GPU, be sure you setup docker for this
[guide](https://github.com/NVIDIA/nvidia-docker/blob/master/README.md#quickstart).

Resolved issue cvat-ai#5984
But the interface probably can be improved

Co-authored-by: Alx-Wo <alexander.wolpert@googlemail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants