Dataset Versions

v2

2023-02-18 7:08pm

Generated on Feb 18, 2023

Dataset Split

Train Set 92%
708Images
Valid Set 8%
59Images
Test Set 0%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±8° Horizontal, ±12° Vertical
Grayscale: Apply to 25% of images
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels