DeepXDE is a library for scientific machine learning and physics-informed learning. It includes implementations for the PINN (physics-informed neural networks), DeepONet (deep operator network) and MFNN (multifidelity neural network) algorithms.

Thread-pool Controls provides Python helpers to limit the number of threads used in the threadpool-backed of common native libraries used for scientific computing and data science (e.g. BLAS and OpenMP).

This package provides a GStreamer plugin that wraps Kaldi's SingleUtteranceNnet2Decoder. It requires iVector-adapted DNN acoustic models. The iVectors are adapted to the current audio stream automatically.

A Python library for reading and writing GGUF & GGML format ML models.

This package provides a command line interface for Lightning AI services.

This package provides a Python wrapper for the SentencePiece unsupervised text tokenizer.

This library is used internally as header-only library by PyTorch.

This package provides easy download of thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

These models can be applied on:

• Text, for tasks like text classification, information extraction, question answering, summarization, translation, and text generation, in over 100 languages.

• Images, for tasks like image classification, object detection, and segmentation.

• Audio, for tasks like speech recognition and audio classification.

Transformer models can also perform tasks on several modalities combined, such as table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.

This package provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community. At the same time, each Python module defining an architecture is fully standalone and can be modified to enable quick research experiments.

Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration between them.

TensorFlow Lite for Microcontrollers is a port of TensorFlow Lite designed to run machine learning models on DSPs, microcontrollers and other devices with limited memory.

cleanlab automatically finds and fixes errors in any ML dataset. This data-centric AI package facilitates machine learning with messy, real-world data by providing clean labels during training.

Captum is a model interpretability and understanding library for PyTorch. Captum contains general purpose implementations of integrated gradients, saliency maps, smoothgrad, vargrad and others for PyTorch models. It has quick integration for models built with domain-specific libraries such as torchvision, torchtext, and others.

This package provides a Python library to easily read single characters and key strokes.

Autograd can automatically differentiate native Python and NumPy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalar-valued functions with respect to array-valued arguments, as well as forward-mode differentiation, and the two can be composed arbitrarily. The main intended application of Autograd is gradient-based optimization.

Random Jungle is an implementation of Random Forests. It is supposed to analyse high dimensional data. In genetics, it can be used for analysing big Genome Wide Association (GWA) data. Random Forests is a powerful machine learning method. Most interesting features are variable selection, missing value imputation, classifier creation, generalization error estimation and sample proximities between pairs of cases.

This package is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including:

• bfloat16: an alternative to the standard float16 format

• float8_*: several experimental 8-bit floating point representations including:

  • float8_e4m3b11fnuz

  • float8_e4m3fn

  • float8_e4m3fnuz

  • float8_e5m2

  • float8_e5m2fnuz

• int4 and uint4: low precision integer types.

This package provides a tool for visualizing live, rich data for Torch and Numpy.

PyTorch is a Python package that provides two high-level features:

• tensor computation (like NumPy) with strong GPU acceleration;

• deep neural networks (DNNs) built on a tape-based autograd system.

You can reuse Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed.

Note: currently this package does not provide GPU support.

This tool provides ordinary differential equation solvers implemented in PyTorch. Backpropagation through ODE solutions is supported using the adjoint method for constant memory cost.

This package enables you to deserialize Lua torch-serialized objects from Python.

TensorPipe provides a tensor-aware channel to transfer rich objects from one process to another while using the fastest transport for the tensors contained therein.

Gloo is a collective communications library. It comes with a number of collective algorithms useful for machine learning applications. These include a barrier, broadcast, and allreduce.

This package provides a fast (zero-copy) and safe (dedicated) format for storing tensors safely.

TensorFlow is a flexible platform for building and training machine learning models. This package provides the "lite" variant for mobile devices.

This package provides a reimplementation of OpenAI's Whisper model using CTranslate2, which is a inference engine for transformer models.