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

Google Research

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

Very random, limited python script to convert a python dictionary into an xml file

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

A Progressive Web App for local file sharing

Gluon CV Toolkit

Bayesian Adaptive Superpixel Segmentation (ICCV 2019)

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

Caffe: a fast open framework for deep learning.

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

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

Blame someone else for your bad code.

Code repository for Part Grouping Network, ECCV 2018

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

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

AMANet pytorch implementation

This is the official pytorch implementation of AutoDebias, an automatic debiasing method for recommendation.

Semantic Segmentation in Pytorch

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

This repository contains code and tools for reading, processing, evaluating on, and visualizing Panoptic Parts datasets. Moreover, it contains code for reproducing our CVPR 2021 paper results.

Pyramid Scene Parsing Network, CVPR2017.

Include mmdetection version of TinyBenchmark. Official link.

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

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

A Simple and Versatile Framework for Object Detection and Instance Recognition

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

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

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