Dataset Versions

v3

2023-11-01 4:18pm

Generated on Nov 1, 2023

Dataset Split

Train Set 83%
351Images
Valid Set 12%
50Images
Test Set 5%
22Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -14° and +14°
Saturation: Between -50% and +50%
Brightness: Between -38% and +38%
Exposure: Between -5% and +5%
Blur: Up to 0.5px
Noise: Up to 2% of pixels