Dataset Versions
Versions
v1
2024-12-19 9:04pm
Generated on Dec 19, 2024
1007 Total Images
View All Images
Dataset Split
Train Set 92%
930Images
Valid Set 1%
10Images
Test Set 7%
67Images
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: ±15° Horizontal, ±15° Vertical
Saturation: Between -30% and +30%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 0.6px
Noise: Up to 0.2% of pixels