This repo is about implementing different approaches of pose estimation and also is a sub-task of the smart hospital bed project :smile:

Last update: Oct 17, 2022

Overview

Pose-Estimation

This repo is a sub-task of the smart hospital bed project which is about implementing the task of pose estimation 😄 Many thanks to the main authors of hrnet-human-pose-estimation project - the project I'd mainly based on.

Setup

Data preparation

I used coco dataset(2017) which can be downloaded here, and the format is just like this:

${POSE_ROOT}
|-- data
`-- |-- coco
    `-- |-- annotations
        |   |-- person_keypoints_train2017.json
        |   `-- person_keypoints_val2017.json
        |-- person_detection_results
        |   |-- COCO_val2017_detections_AP_H_56_person.json
        |   |-- COCO_test-dev2017_detections_AP_H_609_person.json
        `-- images
            |-- train2017
            |   |-- 000000000009.jpg
            |   |-- 000000000025.jpg
            |   |-- 000000000030.jpg
            |   |-- ... 
            `-- val2017
                |-- 000000000139.jpg
                |-- 000000000285.jpg
                |-- 000000000632.jpg
                |-- ...

Dependencies

Here are required packages:

torch
torchvision
numpy
json_tricks
yacs>=0.1.5
Cython

You also need to install cocoapi:

git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
# Install into global site-packages
make install
# Alternatively, if you do not have permissions or prefer
# not to install the COCO API into global site-packages
python3 setup.py install --user
cd ..

Usage

pip install -r requirements.txt
cd src
python3 main.py # update later

Citation

@inproceedings{sun2019deep,
  title={Deep High-Resolution Representation Learning for Human Pose Estimation},
  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
  booktitle={CVPR},
  year={2019}
}

@inproceedings{xiao2018simple,
    author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
    title={Simple Baselines for Human Pose Estimation and Tracking},
    booktitle = {European Conference on Computer Vision (ECCV)},
    year = {2018}
}

This repo is about implementing different approaches of pose estimation and also is a sub-task of the smart hospital bed project :smile:

Related tags

Overview

Pose-Estimation

Setup

Data preparation

Dependencies

Usage

Citation

Owner

Max

PyTorch implementation of MuseMorphose, a Transformer-based model for music style transfer.

[BMVC 2021] Official PyTorch Implementation of Self-supervised learning of Image Scale and Orientation Estimation

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

NeuralForecast is a Python library for time series forecasting with deep learning models

This is a project based on ConvNets used to identify whether a road is clean or dirty. We have used MobileNet as our base architecture and the weights are based on imagenet.

Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)

Implementation of average- and worst-case robust flatness measures for adversarial training.

Use tensorflow to implement a Deep Neural Network for real time lane detection

Pytorch implementation of SELF-ATTENTIVE VAD, ICASSP 2021

Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Official code for our EMNLP2021 Outstanding Paper MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks

Distributed Asynchronous Hyperparameter Optimization better than HyperOpt.

A ssl analyzer which could analyzer target domain's certificate.

Train the HRNet model on ImageNet

COVID-VIT: Classification of Covid-19 from CT chest images based on vision transformer models

Machine Learning Time-Series Platform

Official code for "Stereo Waterdrop Removal with Row-wise Dilated Attention (IROS2021)"

PPLNN is a Primitive Library for Neural Network is a high-performance deep-learning inference engine for efficient AI inferencing

a pytorch implementation of auto-punctuation learned character by character