Dataset Versions

v1

2024-05-24 10:17am

Generated on May 24, 2024

Dataset Split

Train Set 88%
204Images
Valid Set 9%
20Images
Test Set 4%
9Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Hue: Between -7° and +7°
Saturation: Between -16% and +16%
Brightness: Between -9% and +9%
Exposure: Between -7% and +7%