Dataset Versions

v1

2023-07-23 3:24pm

Generated on Jul 23, 2023

Dataset Split

Train Set 95%
396Images
Valid Set 3%
13Images
Test Set 2%
9Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -21° and +21°
Shear: ±1° Horizontal, ±27° Vertical
Grayscale: Apply to 25% of images