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

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

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

Refine high-quality datasets and visual AI models

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

OpenMMLab Pose Estimation Toolbox and Benchmark.

Official DeiT repository

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Dual Attention Network for Scene Segmentation (CVPR2019)

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Deep Metric Learning

Wrapper of 50+ image matching models with a unified interface

MS-Loss: Multi-Similarity Loss for Deep Metric Learning

Pytorch implementation of NetVlad including training on Pittsburgh.

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

Open source implementation of "Spreading Vectors for Similarity Search"

MixVPR: Feature Mixing for Visual Place Recognition (WACV 2023)

Rich Image Visualization with Minimum Dependency (no OpenCV, Matplotlib)

An Open-source Deep Learning Framework for Visual Place Recognition

GSV-Cities: a large-scale dataset for visual place recognition

A lightweight Text-to-Image Retrieval model [Web App]