Dataset Versions

v2

v1

Generated on Aug 17, 2022

Dataset Split

Train Set 87%
429Images
Valid Set 8%
41Images
Test Set 4%
21Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 416x416
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°