Dataset Versions
v1
2022-07-18 1:22pm
Generated on Jul 18, 2022
483 Total Images
View All Images
Dataset Split
Train Set 88%
423Images
Valid Set 8%
40Images
Test Set 4%
20Images
Preprocessing
No preprocessing steps were applied.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -18° and +18°
Shear: ±19° Horizontal, ±18° Vertical
Saturation: Between -46% and +46%
Noise: Up to 1% of pixels
Cutout: 8 boxes with 12% size each