Dataset Versions

v1

2024-09-18 8:27am

Generated on Sep 18, 2024

Dataset Split

Train Set 88%
21Images
Valid Set 8%
2Images
Test Set 4%
1Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -45° and +45°
Shear: ±10° Horizontal, ±14° Vertical
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Exposure: Between -10% and +10%