PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Datasets, Transforms and Models specific to Computer Vision

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

This is a knowledge distillation toolbox based on mmdetection.

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

Benchmark datasets and code used in our paper "DoveNet: Deep Image Harmonization via Domain Verification", CVPR2020. Useful for Image harmonization, image composition/compositing, etc.

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

Channel-wise Distillation for Semantic Segmentation

This repository contains the source code of our work on designing efficient CNNs for computer vision

Fully Convolutional HarDNet for Segmentation in Pytorch

A light-weight, power efficient, and general purpose convolutional neural network

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

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

The code for paper "CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning"

a pytorch-based simple PointRend structure

PyTorch implementation of Guided Image Filtering

SOLO: Segmenting Objects by Locations https://arxiv.org/abs/1912.04488

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

Unofficial implementation of CARAFE: Content-Aware ReAssembly of FEatures. Pure pytorch imp

Antialiasing cnns to improve stability and accuracy. In ICML 2019.