sunny's repositories
computer-vision-raspberrypi
Sample projects for Computer Vision with Raspberry Pi and Movidius Neural Compute Stick
crack_segmentation
This repository contains code and dataset for the task crack segmentation using two architectures UNet_VGG16, UNet_Resnet and DenseNet-Tiramusu
deep-high-resolution-net.pytorch
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
EfficientPose
Scalable single-person pose estimation
facial-landmark-detection-hrnet
A TensorFlow implementation of HRNet for facial landmark detection.
High-Resolution-Remote-Sensing-Semantic-Segmentation-PyTorch
PyTorch实现高分遥感语义分割(地物分类);2019年遥感图像稀疏表征智能分析竞赛-语义分割赛道
human-pose-estimation.pytorch
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
image-segmentation-keras
Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.
lightweight-human-pose-estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
lite_hrnet
Lite-HRNet: A Lightweight High-Resolution Network
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
MobilePose-pytorch
Light-weight Single Person Pose Estimator
RFSong-7993
设计的轻量级RFB进行行人检测,AP达到0.7993,参数量仅有3.1MB,200 FPS
smiles-transformer
Original implementation of the paper "SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery" by Shion Honda et al.
Transformer_Relative_Position_PyTorch
Implement the paper "Self-Attention with Relative Position Representations"
TUPE
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB