🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

The Python programming language

Streamlit — A faster way to build and share data apps.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Federated query engine for AI - The only MCP Server you'll ever need

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

结巴中文分词

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

OpenMMLab Detection Toolbox and Benchmark

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Graph Neural Network Library for PyTorch

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Never use print for debugging again

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Image augmentation for machine learning experiments.

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Python Implementation of Reinforcement Learning: An Introduction

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Ongoing research training transformer models at scale

Parallel computing with task scheduling

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Fast and Accurate ML in 3 Lines of Code

A Python implementation of global optimization with gaussian processes.

A PyTorch implementation of EfficientNet