Dataset Versions

v2

2022-11-09 12:22am

Generated on Nov 9, 2022

Dataset Split

Train Set 88%
462Images
Valid Set 8%
44Images
Test Set 4%
22Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -5° and +5°
Hue: Between -33° and +33°
Saturation: Between -70% and +70%
Brightness: Between -31% and +31%
Exposure: Between -24% and +24%
Noise: Up to 1% of pixels