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 "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

Implementation of the paper "Fine-Tuning Transformers: Vocabulary Transfer"

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

This is the repository for paper NEEDLE: Towards Non-invertible Backdoor Attack to Deep Learning Models.

Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Implementation of ML models like Decision tree, Naive Bayes, Logistic Regression and many other

🔥 Real-time Super Resolution enhancement (4x) with content loss and relativistic adversarial optimization 🔥

PyTorch implementation of the paper:A Convolutional Approach to Melody Line Identification in Symbolic Scores.

4D Human Body Capture from Egocentric Video via 3D Scene Grounding

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Official Implementation of SWAGAN: A Style-based Wavelet-driven Generative Model

NR-GAN: Noise Robust Generative Adversarial Networks

Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21)

Repository of the paper Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models at ML4AD @ NeurIPS 2021.

YOLTv4 builds upon YOLT and SIMRDWN, and updates these frameworks to use the most performant version of YOLO, YOLOv4

[CVPR 2021] 'Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator'

PyTorch implementation of "Simple and Deep Graph Convolutional Networks"

Proto-RL: Reinforcement Learning with Prototypical Representations

This project aim to create multi-label classification annotation tool to boost annotation speed and make it more easier.