rentainhe

visualization

a collection of visualization function

vision-mlp

A collection of SOTA vision mlp models based on Pytorch

ConvNeXt

Code release for ConvNeXt model

rexnet

Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

AdelaiDet

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

bug-solution

a collection of methods to debug

DAB-DETR

[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

deit

Official DeiT repository

einops

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

expt

Experiment. Plot. Tabulate.

gitalk-comment

Save the blog comments for my personal website

Jittor-MLP

Unofficial Implementation of MLP-Mixer, gMLP, resMLP, Vision Permutator, S2MLPv2, RaftMLP, HireMLP, ConvMLP, AS-MLP, SparseMLP, ConvMixer in Jittor and PyTorch! Now, Rearrange and Reduce in einops.layers.jittor are support!! trunc_normal_ is supported for Jittor!!

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

MetaFormer

mmcv

OpenMMLab Computer Vision Foundation

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mmtracking

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

openvqa

A lightweight, scalable, and general framework for visual question answering research

python-accumulations

A collection of excellent python online notes

rentainhe_old.github.io

Personal Website

SeMask-Segmentation

[Preprint] SeMask: Semantically Masked Transformers for Semantic Segmentation.

SimREC

A lightweight codebase for referring expression comprehension and segmentation

Swin-Transformer

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

vision

Datasets, Transforms and Models specific to Computer Vision

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

yolov7

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥