Neural Networks Python Packages

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

spacy

💫 Industrial-strength Natural Language Processing (NLP) in Python

keras

Deep Learning for humans

blis

💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!

onnxruntime-gpu

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

treescope

An interactive HTML pretty-printer for machine learning research in IPython notebooks.

gluonts

Probabilistic time series modeling in Python

equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

dm-haiku

JAX-based neural network library

tensorflow-probability

Probabilistic reasoning and statistical analysis in TensorFlow

torch-ema

Tiny PyTorch library for maintaining a moving average of a collection of parameters.

nemo-toolkit

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

supervisely

Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely Platform for your computer vision task

keras-hub

Deep Learning for humans

dm-control

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

tfp-nightly

Probabilistic reasoning and statistical analysis in TensorFlow

keras-nightly

Deep Learning for humans

optimistix

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

diffrax

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

bittensor

Internet-scale Neural Networks

trulens-core

Evaluation and Tracking for LLM Experiments and AI Agents

trulens

Evaluation and Tracking for LLM Experiments and AI Agents

pypots

A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

keras-nlp

Deep Learning for humans