Dataset Versions

v10

2024-09-03 11:55pm

Generated on Sep 3, 2024

Dataset Split

Train Set 88%
1983Images
Valid Set 8%
188Images
Test Set 4%
89Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 10% of images
Hue: Between -14° and +14°
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels