CMPE593 - Deep Learning for Computer Vision, Term Project This project focuses on replicating FADE, a task-agnostic upsampling operator for encoder-decoder architectures.
While FADE is designed for a variety of tasks, this implementation specifically covers object detection.
- Notebooks under "main-notebooks" were ran in Google Colab
- "src" folder contains all necessary functions which are called in main notebooks.
- "src" folder and its contents were placed on the path defined in the notebooks for import.
- Only file that is not mine is named "FADE_H2L.py" provided by the original authors of the paper.
- Can be found in source repository listed in Resources section.