Dataset Versions

v1

2023-02-09 4:24pm

Generated on Feb 9, 2023

Dataset Split

Train Set 94%
300Images
Valid Set 5%
15Images
Test Set 2%
5Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 256x256

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -35° and +35°
Shear: ±24° Horizontal, ±12° Vertical
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels