Dataset Versions
v3
2024-10-19 11:00am
Generated on Oct 19, 2024
48 Total Images
View All Images
Dataset Split
Train Set 88%
42Images
Valid Set 8%
4Images
Test Set 4%
2Images
Preprocessing
No preprocessing steps were applied.
Augmentations
Outputs per training example: 3
Rotation: Between -21° and +21°
Shear: ±14° Horizontal, ±19° Vertical
Grayscale: Apply to 34% of images
Hue: Between -43° and +43°
Saturation: Between -34% and +34%
Cutout: 4 boxes with 19% size each
Mosaic: Applied
Bounding Box: Flip: Horizontal
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 2.5px
Bounding Box: Noise: Up to 1.64% of pixels