Stars
EXO Gym is an open-source Python toolkit that facilitates distributed AI research.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
Hardware accelerated, batchable and differentiable optimizers in JAX.
A library for differentiable nonlinear optimization
Convert Machine Learning Code Between Frameworks
Optax is a gradient processing and optimization library for JAX.
A Python framework for accelerated simulation, data generation and spatial computing.
JAX - A curated list of resources https://github.com/google/jax
Official code for ICCV 2021 oral paper: Topologically Consistent Multi-View Face Inference Using Volumetric Sampling
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Open3D: A Modern Library for 3D Data Processing
CasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained …
Python interface to the Intel MKL Pardiso library to solve large sparse linear systems of equations
Sparse matrix tools extending scipy.sparse, but with incompatible licenses
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Using modified BiSeNet for face parsing in PyTorch
Decentralized Privacy-Preserving Proximity Tracing -- Documents
This repository contains the source code for the paper First Order Motion Model for Image Animation
Code release for NeRF (Neural Radiance Fields)
COVID19 case numbers of Cantons of Switzerland and Principality of Liechtenstein (FL). The data is updated at best once a day (times of collection and update may vary). Start with the README.
Mitsuba 2: A Retargetable Forward and Inverse Renderer
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data