Dataset Versions
Versions
v1
2024-04-22 9:28am
Generated on Apr 22, 2024
218 Total Images
View All Images
Dataset Split
Train Set 84%
183Images
Valid Set 10%
22Images
Test Set 6%
13Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -4° and +4°
Saturation: Between -16% and +16%
Exposure: Between -5% and +5%