Google Research

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

Caffe: a fast open framework for deep learning.

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

A Progressive Web App for local file sharing

Blame someone else for your bad code.

Deep Residual Learning for Image Recognition

Gluon CV Toolkit

[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

A Simple and Versatile Framework for Object Detection and Instance Recognition

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

Pyramid Scene Parsing Network, CVPR2017.

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

Fast, modular reference implementation and easy training of Semantic Segmentation algorithms in PyTorch.

Semantic Segmentation in Pytorch

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

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

Tiny Face Detector, CVPR 2017

[CVPR 2021 & IJCV 2024] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Please choose the openseg.pytorch project for the updated code that achieve SOTA on 6 benchmarks!

SOS IROS 2018 GOOGLE; StereoNet ECCV2018 GOOGLE; ActiveStereoNet ECCV2018 Oral GOOGLE; HITNET CVPR2021 GOOGLE；PLUME Uber ATG

ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor

Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

A fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please see the original readme.

[CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching

Deep Paper Gestalt

Code repository for Part Grouping Network, ECCV 2018

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

CRF-RNN PyTorch version http://crfasrnn.torr.vision