Dataset Versions
v3
2024-11-01 8:55am
Generated on Nov 1, 2024
292 Total Images
View All Images
Dataset Split
Train Set 87%
254Images
Valid Set 10%
28Images
Test Set 3%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 2
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Grayscale: Apply to 3% of images
Hue: Between -19° and +19°
Saturation: Between -23% and +23%
Brightness: Between -15% and +15%
Exposure: Between -13% and +13%
Blur: Up to 0.6px