Dataset Versions

v7

2023-12-28 9:48pm

Generated on Dec 28, 2023

Dataset Split

Train Set 87%
849Images
Valid Set 8%
82Images
Test Set 4%
41Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 128x128
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Blur: Up to 2.5px
Cutout: 5 boxes with 10% size each