Dataset Versions
Versions
v3
2022-12-02 8:58pm
Generated on Dec 3, 2022
79 Total Images
View All Images
Dataset Split
Train Set 87%
69Images
Valid Set 9%
7Images
Test Set 4%
3Images
Preprocessing
Auto-Orient: Applied
Static Crop: 36-75% Horizontal Region, 25-92% Vertical Region
Resize: Fit (reflect edges) in 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Hue: Between -58° and +58°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%