Dataset Versions

v2

2024-01-02 9:51pm

Generated on Jan 2, 2024

Dataset Split

Train Set 88%
1206Images
Valid Set 4%
57Images
Test Set 8%
110Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Saturation: Between -28% and +28%
Brightness: Between -15% and +15%
Exposure: Between -11% and +11%
Blur: Up to 2.5px
Noise: Up to 0.61% of pixels