Skip to content

Meg-R/ict3104_team_05

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

115 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ICT3104 Team 5 💣

A Jupyter Notebook that combines the work of FollowYourPose & MMPose.

  • Dual platform support
  • Dynamic MMPose Inference
  • Streamlined FYP Inference with MMPose
  • Inference Output with customisable formatting (Stitch/Superimpose)
  • Inbuilt Stable Diffusion Model Fine-tuning
  • Trained Model Testing
  • Automatic Scoring using Euclidean Distance Normalisation & Manual Model Scoring System
  • Trained Model Testing results comparison/visualisation analysis

👥 Team Members

Name ID
Maximus Lee 2100724
Aloysius Woo 2100891
Jin Zhenglong 2101002
Ai Xin 2102468
Huai Fu 2001188

👾 Demos

  • 🏗 demo.ipynb

    • A more traditional approach to running the program. Cells must be run sequentially. Some cells contain functionality, some cells provide the actual user functionality.
    • More suited for development and maintainence. Steps are more granular.
  • demo_bombastic.colab

    • All functionality is accessible through a single user interface window.
    • More suited for end-users as all functionalities are streamlined for easier use.

🖥️ Quick Start

  • 🌈 Google Colab

demo.ipynb

Run demo.ipynb in Google Colab

demo_bombastic.ipynb

Run demo_bombastic.ipynb in Google Colab

  • 🪟 Local (Windows)
  1. Download and install Python 3.8.
  2. Install git, ensure LFS support is checked.
  3. Install ImageMagick. Installation instructions are at link.
  4. Install FFmpeg. Installation instructions are at link.
  5. Run batch file at other_files/batch_files/create_venv.bat to initialise virtual environment.
cd other_files/batch_files && create_venv.bat
  1. To launch Jupyter Notebook in your browser, run demos/local_windows_demo.bat or demos/local_windows_demo_bombastic.bat.
cd demos && local_windows_demo.bat
cd demos && local_windows_demo_bombastic.bat

⭐ Special Thanks

About

A Jupyter Notebook Wrapper that combines the work of FollowYourPose & MMPose.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 74.8%
  • Jupyter Notebook 24.3%
  • C++ 0.7%
  • Shell 0.2%
  • Dockerfile 0.0%
  • Batchfile 0.0%