v5

2024-08-19 7:59am

Generated on Aug 19, 2024

Dataset Split

Train Set 87%
153Images
Valid Set 9%
15Images
Test Set 4%
7Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 100% of images
Hue: Between -80° and +80°
Brightness: Between -47% and +47%
Blur: Up to 1px
Noise: Up to 4.97% of pixels