Dataset Versions
Versions
v2
2023-07-11 4:45pm
Generated on Jul 11, 2023
517 Total Images
View All Images
Dataset Split
Train Set 88%
453Images
Valid Set 6%
32Images
Test Set 6%
32Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 26% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±19° Horizontal, ±15° Vertical
Grayscale: Apply to 100% of images
Hue: Between -155° and +155°
Saturation: Between -59% and +59%
Brightness: Between -33% and +33%
Exposure: Between -14% and +14%
Blur: Up to 3px
Noise: Up to 4% of pixels
Cutout: 14 boxes with 4% size each