[build-system] requires = ["setuptools>=61.0", "wheel"] build-backend = "setuptools.build_meta" [project] name = "Grounded-SAM-2" version = "1.0" description = "Grounded SAM 2: Ground and Track Anything in Videos" readme = "README.md" requires-python = ">=3.10.0" license = { text = "Apache 2.0" } authors = [{ name = "Meta AI", email = "segment-anything@meta.com" }] keywords = ["segmentation", "computer vision", "deep learning"] dependencies = [ "torch>=2.3.1", "torchvision>=0.18.1", "numpy>=1.24.4", "tqdm>=4.66.1", "hydra-core>=1.3.2", "iopath>=0.1.10", "pillow>=9.4.0", "opencv-python-headless>=4.11.0.86", "supervision>=0.26.1", "pycocotools>=2.0.10", "transformers>=4.55.1", "addict>=2.4.0", "yapf>=0.43.0", "timm>=1.0.19", "pdf2image>=1.17.0", ] [project.optional-dependencies] notebooks = [ "matplotlib>=3.9.1", "jupyter>=1.0.0", "opencv-python>=4.7.0", "eva-decord>=0.6.1", ] interactive-demo = [ "Flask>=3.0.3", "Flask-Cors>=5.0.0", "av>=13.0.0", "dataclasses-json>=0.6.7", "eva-decord>=0.6.1", "gunicorn>=23.0.0", "imagesize>=1.4.1", "pycocotools>=2.0.8", "strawberry-graphql>=0.243.0", ] dev = [ "black==24.2.0", "usort==1.0.2", "ufmt==2.0.0b2", "fvcore>=0.1.5.post20221221", "pandas>=2.2.2", "scikit-image>=0.24.0", "tensorboard>=2.17.0", "pycocotools>=2.0.8", "tensordict>=0.5.0", "opencv-python>=4.7.0", "submitit>=1.5.1", ] [tool.setuptools] # extensions = [{ name = "sam2._C", sources = ["sam2/csrc/connected_components.cu"] }] packages = ["sam2", "grounding_dino"]