Dataset Versions

v9

2023-11-24 7:28pm

Generated on Nov 24, 2023

Dataset Split

Train Set 88%
1074Images
Valid Set 12%
153Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 512x512
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Exposure: Between -30% and +30%
Blur: Up to 2px
Noise: Up to 25% of pixels
Cutout: 5 boxes with 5% size each
Mosaic: Applied