Dataset Versions

v1

2024-01-11 10:50pm

Generated on Jan 11, 2024

Dataset Split

Train Set 87%
192Images
Valid Set 9%
20Images
Test Set 4%
9Images

Preprocessing

Resize: Fill (with center crop) in 1200x1200

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Noise: Up to 1.88% of pixels