Dataset Versions

v3

2024-01-25 4:13pm

Generated on Jan 25, 2024

Dataset Split

Train Set 88%
141Images
Valid Set 8%
13Images
Test Set 4%
7Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 960x960

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Grayscale: Apply to 15% of images
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%