Dataset Versions

v7

2024-11-08 4:38am

Generated on Nov 8, 2024

Dataset Split

Train Set 88%
765Images
Valid Set 8%
73Images
Test Set 4%
36Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Exposure: Between -40% and +40%
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Exposure: Between -20% and +20%