Dataset Versions
v2
2023-12-07 8:43am
Generated on Dec 7, 2023
626 Total Images
View All Images
Dataset Split
Train Set 88%
549Images
Valid Set 8%
52Images
Test Set 4%
25Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 50% of images
Hue: Between -66° and +66°
Saturation: Between -48% and +48%
Brightness: Between -28% and +28%
Exposure: Between -9% and +9%
Blur: Up to 1.5px
Noise: Up to 5% of pixels
Cutout: 2 boxes with 10% size each