Skip to content

Add Docker Support for AmadeusGPT (SAM2) and SAM Image Segmentation #63

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

Open
wants to merge 9 commits into
base: main
Choose a base branch
from

Conversation

xiu-cs
Copy link

@xiu-cs xiu-cs commented May 9, 2025

This pull request introduces several significant changes, primarily focused on adding support for SAM2 image segmentation, Docker configuration updates. Below are the most important changes grouped by theme:

Docker Configuration Updates:

  • Added a new Dockerfile (simplified version) for setting up a containerized environment with PyTorch, DeepLabCut, and various other tools. It includes user creation, Oh My Zsh installation, and GPU support. (Dockerfile, DockerfileR1-R54)
  • Introduced Dockerfile.sam2 (development version) for SAM2-specific configurations, including cloning and setting up the SAM2 repository and its dependencies. (Dockerfile.sam2, Dockerfile.sam2)

Makefile Enhancements:

  • Added new Makefile targets for building (build), running (run), and accessing (exec) Docker containers. These commands streamline the development workflow and support volume mounting for local project directories. (Makefile, MakefileR5-R37)

SAM2 Image Segmentation (Dev version):

  • Implemented sam2_image_seg in sam2_image.py, a function for performing image segmentation using the SAM2 model. It supports prompts, GPU acceleration, and visualization of segmentation masks. (sam2_image.py, sam2_image.py)

@MMathisLab MMathisLab requested a review from yeshaokai May 13, 2025 07:35
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.

1 participant