Dataset Versions

v1

2024-09-04 8:23pm

Generated on Sep 4, 2024

Dataset Split

Train Set 88%
63Images
Valid Set 8%
6Images
Test Set 4%
3Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Brightness: Between -15% and +15%
Blur: Up to 2.5px
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Shear: ±10° Horizontal, ±10° Vertical