#deep-learning

SDK for running DeepLabCut on a live video stream

GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.

Graph Neural Networks in Julia

Pure Rust DLPack implementation for zero-copy tensor interoperability

Laplace approximations for Deep Learning.

Generative modeling for JAX/Flax NNX: VAEs, GANs, DDPM/DDIM/score/DiT/latent diffusion, normalizing flows, energy-based, autoregressive and geometric (SE(3), protein, point cloud, mesh) models; image, text, audio, molecular, protein, tabular and time-series modalities; a shared Trainer with callbacks and extensions; evaluation through calibrax.

Effector - a Python package for global and regional effect methods

Hardware accelerated, batchable and differentiable optimizers in JAX.

A framework for state-of-the-art pre-trained bio foundation models on genomics and transcriptomics modalities.

A Data Streaming Library for Efficient Neural Network Training

A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.

Probabilistic reasoning and statistical analysis in TensorFlow

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!

SemiBin: metagenomics binning with self-supervised deep learning

View model summaries in PyTorch!

JAX/Flax NNX training infrastructure: device meshes and SPMD sharding, an Orbax checkpoint store, early stopping and callbacks, W&B and MLflow logging.

ClearML Agent - MLOps/LLMOps made easy. MLOps/LLMOps scheduler & orchestration solution

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

Deep learning framework for proteomics

Unofficial Rust bindings to Apple's mlx framework

The RWTH extensible training framework for universal recurrent neural networks

Rust bindings for the C++ api of PyTorch.

Nx-powered Neural Networks

Train and serve LLMs at extreme speed and massive throughput.