Dataset Versions

v1

2023-12-28 3:15pm

Generated on Dec 28, 2023

Dataset Split

Train Set 88%
126Images
Valid Set 8%
12Images
Test Set 4%
6Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -20° and +20°
Hue: Between -52° and +52°
Saturation: Between -25% and +25%
Brightness: Between -40% and +40%
Exposure: Between -29% and +29%
Blur: Up to 2.5px
Mosaic: Applied