Dataset Versions
v1
2023-12-03 5:25am
Generated on Dec 3, 2023
353 Total Images
View All Images
Dataset Split
Train Set 88%
309Images
Valid Set 8%
29Images
Test Set 4%
15Images
Preprocessing
Auto-Orient: Applied
Static Crop: 20-77% Horizontal Region, 20-82% Vertical Region
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -10° and +10°
Saturation: Between -20% and +20%
Brightness: Between -25% and +25%
Exposure: Between -8% and +8%
Blur: Up to 3.5px
Noise: Up to 4% of pixels