DNP project.

Re-produce a system to detection, tracking and analysis student action.

• OS: Ubuntu 22.04.
• Docker, Cuda 12.1 (cpu is oke but slower)
• Pytorch 2.1
• Confluent kafka
• MUST have more than 8gb of RAM
• Familiar with Openmmlab, mmTracking, mmPose, Ultralytics

$ pip3 install torch torchvision torchaudio
$ pip install -U openmim
$ mim install mmengine
$ pip install -r requirements.txt

• Run confluent kafka docker docker-compose.yaml file.

docker compose up

• Create topics first: python create_topics.py

• Open 4 terminal window and run this by order.

$ python Save_video_process.py
$ python Pose_process.py
$ python Tracking_process.py
$ python Read_frame_process.py

• Or just one line

$ chmod +x run_local.sh
$ ./run_local.sh

Any advise for common problems or issues.

God bless you :)

Contributors names and contact info

• @NTThong

• 0.2
  • Various bug fixes and optimizations
  • See commit change or See release history
• 0.1
  • Initial Release

This project is licensed under the [NAME HERE] License - see the LICENSE.md file for details

Inspiration, code snippets, etc.

• awesome-readme
• PurpleBooth
• dbader
• zenorocha
• fvcproductions