Dataset Versions

v1

2024-12-07 4:24pm

Generated on Dec 7, 2024

Dataset Split

Train Set 96%
3078Images
Valid Set 4%
114Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -10° and +10°
Shear: ±6° Horizontal, ±5° Vertical
Brightness: Between -18% and +18%
Exposure: Between -11% and +11%
Blur: Up to 0.8px
Noise: Up to 0.3% of pixels