Dataset Versions

v1

2022-02-14 7:52pm

Generated on Feb 14, 2022

Dataset Split

Train Set 87%
402Images
Valid Set 9%
40Images
Test Set 5%
21Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -45° and +45°
Grayscale: Apply to 25% of images