holygen Goto Github PK

py-r-fcn

R-FCN with joint training and python support

pytorch-cnn-visualizations

Pytorch implementation of convolutional neural network visualization techniques

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

pytorch-enet

PyTorch implementation of ENet

pytorch-grad-cam

PyTorch implementation of Grad-CAM

pytorch-hardnet

35% faster than ResNet: Harmonic DenseNet, A low memory traffic network

pytorch-mobilenet-v2

A PyTorch implementation of MobileNet V2 architecture and pretrained model.

pytorch-opcounter

Count the MACs / FLOPs of your PyTorch model.

pytorch-segmentation-toolbox

PyTorch Implementations for DeeplabV3 and PSPNet

radialpose

C++ implementation of radial distortion absolute pose solvers.

radialsfm

1D Radial Structure-from-Motion (Larsson et al., ECCV 2020)

radial_quadrifocal

ransaclib

Template-based implementation of RANSAC and its variants in C++

rddc2020

road damage detection challenge 2020

realtime_multi-person_pose_estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

reid-strong-baseline

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

reid_tutorial_slides

《深度学习与行人重识别》课程课件

reppointsv2

resnest

ResNeSt: Split-Attention Networks

rethinking_bottleneck_design

roberta_zh

RoBERTa中文预训练模型: RoBERTa for Chinese

rtabmap

RTAB-Map library and standalone application

saccadenet

sar-strong-baseline-for-text-recognition

SAR: A Simple and Strong Baseline for Irregular Text Recognition

scaledyolov4

segmentron

Support Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

self-driving-car

Udacity Self-Driving Car Engineer Nanodegree projects.

semseg

Semantic Segmentation in Pytorch

senet

Squeeze-and-Excitation Networks

sfsegnets

Implementation of Our ECCV oral paper: Semantic Flow for Fast and Accurate Scene Parsing