Dataset Versions

v5

2024-08-19 10:38am

Generated on Aug 19, 2024

Dataset Split

Train Set 87%
3147Images
Valid Set 9%
313Images
Test Set 4%
162Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -12° and +12°
Shear: ±10° Horizontal, ±10° Vertical
Exposure: Between -10% and +10%
Noise: Up to 0.81% of pixels

Similar Projects

See More