Dataset Versions

v1

2024-12-06 12:34pm

Generated on Dec 6, 2024

Dataset Split

Train Set 94%
1866Images
Valid Set 6%
115Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -10° and +10°
Shear: ±2° Horizontal, ±2° Vertical
Hue: Between -5° and +5°
Brightness: Between -10% and +10%
Exposure: Between -10% and +10%
Blur: Up to 1.5px
Noise: Up to 1.01% of pixels
Cutout: 8 boxes with 3% size each