🤗 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

Inference code for Llama models

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Graph Neural Network Library for PyTorch

Datasets, Transforms and Models specific to Computer Vision

PyTorch implementations of Generative Adversarial Networks.

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

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Hackable and optimized Transformers building blocks, supporting a composable construction.

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

ImageBind One Embedding Space to Bind Them All

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

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Official DeiT repository

3D ResNets for Action Recognition (CVPR 2018)

Differentiable architecture search for convolutional and recurrent networks

OpenMMLab Pre-training Toolbox and Benchmark

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

pytorch tutorial for beginners

DeepLab v3+ model in PyTorch. Support different backbones.

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

Learning Chinese Character style with conditional GAN

Pytorch framework for doing deep learning on point clouds.

Painter & SegGPT Series: Vision Foundation Models from BAAI