Tensors and Dynamic neural networks in Python with strong GPU acceleration
- neural-network
- autograd
- gpu
- numpy
Repository Index
59,621 visible repositories in the index
1–24 of 96 · Most stars
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
NumPy & SciPy for GPU
- cuda
- cudnn
- cublas
- cusolver
Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
🔩 Like builtins, but boltons. 250+ constructs, recipes, and snippets which extend (and rely on nothing but) the Python standard library. Nothing like Michael Bolton.
- python
- utilities
- cache
- data-structures
A Python based monitoring and tracking tool for Plex Media Server.
- plex
- plexpy
- python
- monitoring
Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
A hardware-agnostic SDK for optimization problems: define a problem once, then lower it to any quantum or classical solver
- constraint-programming
- quantum-computing
- quadratic-programming
A PyTorch Library for Accelerating 3D Deep Learning Research
- pytorch
- 3d-deep-learning
- neural-networks
- differentiable-rendering
A contact solver for physics-based simulations involving 👚 shells, 🪵 solids, 🪢 rods, 🧱 rigid bodies and ⏳ sand.
- cloth
- collision
- contact
- physics
A library for scientific machine learning and physics-informed learning
- neural-network
- deep-learning
- scientific-machine-learning
- pinn
Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians and comes with a large set of tools for scenario creation.
- traffic
- simulation
- transport
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
Scenic: A Jax Library for Computer Vision Research and Beyond
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
- tensorflow
- deep-neural-network
- genomics
- science
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
Code for running RFdiffusion
NSGA2, NSGA3, R-NSGA3, MOEAD, Genetic Algorithms (GA), Differential Evolution (DE), CMAES, PSO
- optimization
- multi-objective-optimization
- nsga2
- nsga3
POT : Python Optimal Transport
- optimal-transport
- numerical-optimization
- machine-learning
- emd
PyWavelets - Wavelet Transforms in Python
- wavelets
- wavelet-transform
- signal-processing
- image-processing
This package contains deep learning models and related scripts for RoseTTAFold
A python module for scientific analysis of 3D data based on VTK and Numpy
- 3d-graphics
- vtk
- 3d
- mesh
An implementation of chunked, compressed, N-dimensional arrays for Python.
- zarr
- ndimensional-arrays
- compressed
- python