Dataset Versions

v8

2024-08-17 10:35pm

Generated on Aug 17, 2024

Dataset Split

Train Set 87%
1173Images
Valid Set 8%
112Images
Test Set 4%
56Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Noise: Up to 1.25% of pixels