Dataset Versions

v8

2023-07-31 10:19pm

Generated on Jul 31, 2023

Dataset Split

Train Set 88%
1320Images
Valid Set 8%
126Images
Test Set 4%
62Images

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: ±15° Horizontal, ±15° Vertical
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels