Dataset Versions

v3

2024-11-07 9:26am

Generated on Nov 7, 2024

Dataset Split

Train Set 92%
965Images
Valid Set 5%
55Images
Test Set 3%
28Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Brightness: Between -15% and +15%