🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

The simplest, fastest repository for training/finetuning medium-sized GPTs.

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

OpenMMLab Detection Toolbox and Benchmark

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

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

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Minimal PyTorch implementation of YOLOv3

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

AI Toolkit for Healthcare Imaging

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

Code for visualizing the loss landscape of neural nets

EVA Series: Visual Representation Fantasies from BAAI

Schedule-Free Optimization in PyTorch

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

PyTorch extensions for fast R&D prototyping and Kaggle farming

A PyTorch library and evaluation platform for end-to-end compression research