spectrumAI

detectron2

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

howto-make-more-money

程序员如何优雅的挣零花钱，2.0版，升级为小书了。Most of this not work outside China , so no English translate

deep-residual-networks

Deep Residual Learning for Image Recognition

awesome-lane-detection

A paper list of lane detection.

DANet

Dual Attention Network for Scene Segmentation (CVPR2019)

lanenet-lane-detection

Unofficial implemention of lanenet model for real time lane detection

PyTorch-Encoding

A CV toolkit for my papers.

pytorch_scatter

PyTorch Extension Library of Optimized Scatter Operations

involution

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

Efficient-Segmentation-Networks

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

SAN

Exploring Self-attention for Image Recognition, CVPR2020.

EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

docker-pyinstaller

PyInstaller for Linux and Windows inside Docker

LaneGCN

[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting

dec

Stand-Alone-Self-Attention

Implementing Stand-Alone Self-Attention in Vision Models using Pytorch

superpixel_fcn

[CVPR‘20] SpixelFCN: Superpixel Segmentation with Fully Convolutional Network

Lightweight-Segmentation

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).

CGNet

CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]

ContextPrior

Implementation for "Context Prior for Scene Segmentation"

segaware

Segmentation-Aware Convolutional Networks Using Local Attention Masks

resuneta

mxnet source code for the resuneta semantic segmentation models

W-Net

W-Net: A Deep Model for Fully Unsupervised Image Segmentation

simple_sagemaker

A *simpler* and *cheaper* way to distribute work (python/shell/training) code on machines of your choice in the (AWS) cloud

sentinel1_denoise_rs

This library provides algorithms to remove noise floor intensity patterns that are prevalent in Sentinel-1 cross-polarized images in EW mode, and to a lesser degree IW mode. This is provided in four ways: a command line interface, a Python interface, a Rust interface, and a C interface.