Dataset Versions

v4

2024-12-23 11:53am

Generated on Dec 23, 2024

Dataset Split

Train Set 88%
861Images
Valid Set 8%
81Images
Test Set 4%
41Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 800x800

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -10° and +10°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -10% and +10%
Noise: Up to 1.8% of pixels

Similar Projects

See More