xiaoye77 Goto Github PK

pytorch-tp-gan

pytorch replicate of TP-GAN "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis"

pytorch-unet

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

pytorch2caffe

Convert PyTorch model to Caffemodel

pytorch_blazeface

Unofficial PyTorch implementation of BlazeFace

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Up to 100FPS landmark inference on CPU.

pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

pytorch_retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

pytorch_segmentation

Semantic segmentation models, datasets and losses implemented in PyTorch.

pytorchtocaffe

Pytorch model to caffe model, supported pytorch 0.3, 0.3.1, 0.4, 0.4.1 ,1.0 , 1.0.1

real-time-multi-target-tracking

Real-time Multi-Target Tracking using region-based fully convolutional neural network

real-world-masked-face-dataset

Real-World Masked Face Dataset，口罩人脸数据集

real_time_object_detection_and_tracking

YOLOv2 and MobileNet_SSD detection algorithms used along with KCF object tracker

realsr

Real-World Super-Resolution via Kernel Estimation and Noise Injection

realtime-action-recognition

Multi-person real-time recognition (classification) of 9 actions based on human skeleton from OpenPose and a 0.5-second window.

refinedet

Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018

reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

repulsion_loss

Pytorch implementation of Repulsion Loss on RetinaNet

repulsion_loss_ssd

Repulsion Loss: Detecting Pedestrians in a Crowd. https://arxiv.org/abs/1711.07752

resnet-18-caffemodel-on-imagenet

ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%

resnet-protofiles

Caffe Protofiles for MSRA ResNet: train prototxt

resnext-1

Reproduce ResNet-v3(Aggregated Residual Transformations for Deep Neural Network) with Caffe

retinaface

Reimplement RetinaFace use C++ and TensorRT

retinaface-cpp

RetinaFace detector with C++

retinaface.pytorch

Reimplement RetinaFace using PyTorch.

retinaface_tensorrt

tensorRT retinaface mobilenet

revgan

RevGAN implementation in PyTorch. We extend the Pix2pix and CycleGAN framework by exploring approximately invertible architectures in 2D and 3D. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep without requiring additional memory. In the paper we demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.

rknn_demo

rknputool

RKNPUTool

rmpe

RMPE: Regional Multi-person Pose Estimation, forked from Caffe. Research purpose only.

rotate-and-render

Code for Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images (CVPR 2020)