Dataset Versions
Versions
v1
2025-01-03 3:37pm
Generated on Jan 3, 2025
194 Total Images
View All Images
Dataset Split
Train Set 85%
165Images
Valid Set 9%
18Images
Test Set 6%
11Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 512x512
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 19% Maximum Zoom
Rotation: Between -12° and +12°
Shear: ±7° Horizontal, ±7° Vertical
Grayscale: Apply to 25% of images
Hue: Between -24° and +24°
Saturation: Between -35% and +35%
Brightness: Between -23% and +23%
Exposure: Between -16% and +16%
Blur: Up to 0.3px
Noise: Up to 0.14% of pixels