Project Documentation

TODOs

• MultiVideo(...)

  • [V] Fixing name of video
  • [V] Returning when all videos finished
  • [V] Adding a pause function
  • [V] Adding a toggle for showing video paths
  • [V] Adding a toggle for showing progress percentage
  • [V] Adding a toggle for full screen
  • [ ] Making it C++ with OpenCV and OpenGL with CUDA support

• process_decider(...)

  • - Add support for C++ files.
  • - Add support for CUDA files.
  • - Add support for other file types if needed.

• build_vf_filter(...)

  • - Add support Rotation and maybe save the rotated video

• detect_drop(...)

  • Going to test with C.

• PE_Generator(...)

  • Check position encoding yields a better results or velocity encoding.
  • Position encoding is to fix the width of the PE to 1246 and Velocity encoding it to calculate the length of the images and then resize width to 1245.
  • Generate positional encodings for a set of images.

  make_PE_image_Folder(...)

  • Test with super resolution images.
  • Test with padding images. Right now I'm gonna prototype with resizing the result image and feed it to the model.
  • Later test with velocity encoding.

• hard_negative_mining(...)

  • - Add handler for different model types (e.g., CNN, LSTM)

  train(...)

  • - Plot training loss over epochs real time in the terminal or a window

• extract_tag_section(...)

  • Finish the implementation to extract the section based on the tag.
  • Add hyperlink to functions
  • Extend it to bug fix and HACK

• main2(...)

  • - Add more functionality to this program.
  • - Implement error handling.
  • - Consider using modern C++ features for better performance and readability.

FIXMEs

HACKs

XXXs

Project Documentation