Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Repository Index
107,098 visible repositories in the index
1–24 of 52 · Most stars
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
📽 Highly Optimized 2D / 3D Graphics Math (glm) for C
Graphormer is a general-purpose deep learning backbone for molecular modeling.
- graph
- transformer
- deep-learning
- ai4science
PyWavelets - Wavelet Transforms in Python
- wavelets
- wavelet-transform
- signal-processing
- image-processing
Simple Ants simulator
- cpp
- simulation
- realtime
- 2d
a Fast Fourier Transform (FFT) library that tries to Keep it Simple, Stupid
Fast, modern C++ DSP framework, FFT, Sample Rate Conversion, FIR/IIR/Biquad Filters (SSE, AVX, AVX-512, ARM NEON, RISC-V RVV)
Linear algebra, eigenvalues, FFT, Bessel, elliptic, orthogonal polys, geometry, NURBS, numerical quadrature, 3D transfinite interpolation, random numbers, Mersenne twister, probability distributions, optimisation, differential equations.
- scientific-computing
- linear-algebra
- differential-equations
- sparse-systems
Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library
- vulkan
- fft
- convolution
- r2c
A .NET GIS solution that is fast and reliable for the .NET platform.
- topology
- nts
- sfs
- c-sharp
Implementation of Alphafold 3 from Google Deepmind in Pytorch
- artificial-intelligence
- deep-learning
- attention-mechanisms
- denoising-diffusion
An acausal modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning and automated transformations of differential equations
- differential-equations
- ode
- dae
- ordinary-differential-equations
Primary repository for the Trilinos Project
- snl-science-libs
- sandia-national-laboratories
- hpsf
- scientific-computing
Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.
- aerodynamics
- airplane
- cfd
- mdo
cvc5 is an open-source automatic theorem prover for Satisfiability Modulo Theories (SMT) problems.
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
- medical-imaging
- medical-ai
- deep-learning
- machine-learning
Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet
- pytorch
- wavelet
- wavelet-transform
- filterbank
Astronomy Engine: multi-language calculation of Sun, Moon, and planet positions. Predicts lunar phases, eclipses, transits, oppositions, conjunctions, equinoxes, solstices, rise/set times, and other events. Provides vector and angular coordinate transforms among equatorial, ecliptic, horizontal, and galactic orientations.
Formula Recognition & Office Editing | Handwriting & PDF to LaTeX/Markdown | Secure API Integrations.
- deep-learning
- pytorch
- im2latex
- image2text
A Python library for designing chips (Photonics, Analog, Quantum, MEMS), PCBs, and 3D-printable objects. We aim to make hardware design accessible, intuitive, and fun—empowering everyone to build the future.
- python
- gdsii
- gds
- eda
PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
All Stanford Cheatsheets: Artificial Intelligence, Transformers, LLMs, Deep Learning, Machine Learning, Probabilities, Statistics, Algebra and Calculus.
- artificial-intelligence
- cheetsheet
- convolutional-neural-networks
- data-science