For these analyses you need the data which is published as Zenodo called: Database for "Automatic Detection of Instream Large Wood in Videos Using Deep Learning"

Sampling and data augmentation stategies are included in the repository.

For the training of the YOLOv4, use the following repository: https://github.com/pjreddie/darknet
For analysis of the YOLOv4 model using yolime, use the following repository: https://github.com/AntMorais/yolime