Dataset Versions

v1

2024-12-24 2:30pm

Generated on Dec 24, 2024

Dataset Split

Train Set 96%
945Images
Valid Set 4%
36Images
Test Set 1%
7Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±8° Horizontal, ±15° Vertical
Grayscale: Apply to 13% of images
Hue: Between -19° and +19°
Saturation: Between -17% and +17%
Brightness: Between -13% and +13%
Blur: Up to 2.5px

Similar Projects

See More