Dataset Versions
v5
2024-11-24 4:16pm
Generated on Nov 24, 2024
240 Total Images
View All Images
Dataset Split
Train Set 88%
210Images
Valid Set 8%
20Images
Test Set 4%
10Images
Preprocessing
Auto-Orient: Applied
Static Crop: 8-92% Horizontal Region, 25-54% Vertical Region
Resize: Fit (reflect edges) in 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%