Dataset Versions

v7

2024-10-31 2:15pm

Generated on Oct 31, 2024

Dataset Split

Train Set 87%
312Images
Valid Set 13%
46Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±12° Horizontal, ±12° Vertical
Blur: Up to 2.5px
Noise: Up to 1.05% of pixels
Cutout: 8 boxes with 5% size each