2 Repos
Awesome GitHub RepositoriesCross-Framework Tensor Dispatch
Abstraction layers that enable tensor operations to run across multiple backends like PyTorch, TensorFlow, and JAX.
Distinct from Tensor Computation Backends: Candidates focus on specific backends or debuggers; this is about the abstraction/dispatch layer across frameworks.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Cross-Framework Tensor Dispatch. Refine with filters or upvote what's useful.
Awesome Cross-Framework Tensor Dispatch GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- kornia/kornia
kornia/kornia
11,238Auf GitHub ansehenKornia is a differentiable computer vision library and cross-framework tensor vision toolset. It implements vision operations as differentiable tensors to enable integration into deep learning pipelines and supports the transpilation of operations across PyTorch, TensorFlow, JAX, and NumPy. The project provides specialized toolsets for geometric vision and stereo depth, including algorithms for 3D scene reconstruction, camera calibration, and pose estimation. It further distinguishes itself as a differentiable image augmentation framework, applying random geometric and color transformations w
Abstracts tensor operations to allow the same vision logic to run across PyTorch, TensorFlow, JAX, and NumPy.
Pythonartificial-intelligencecomputer-visiondeep-learning - pythonot/pot
PythonOT/POT
2,751Auf GitHub ansehenPOT is an optimal transport library providing a collection of solvers for computing Wasserstein, Gromov-Wasserstein, and Fused Gromov-Wasserstein distances between probability distributions. It functions as a differentiable tensor framework that integrates with various tensor libraries to enable automatic differentiation and GPU acceleration. The project is distinguished by its ability to align data distributions across different metric spaces by comparing internal relational structures rather than coordinates. It implements mathematical optimization algorithms as differentiable layers, allow
Provides an abstraction layer that allows tensor operations to run across multiple backends including PyTorch, TensorFlow, and JAX.
Pythondomain-adaptationemdgromov-wasserstein
