Dataset Versions
v4
2023-10-06 10:24am
Generated on Oct 6, 2023
15954 Total Images
View All Images
Dataset Split
Train Set 88%
14037Images
Valid Set 5%
815Images
Test Set 7%
1102Images
Preprocessing
Auto-Orient: Applied
Static Crop: 9-73% Horizontal Region, 14-87% Vertical Region
Resize: Fit (white edges) in 224x224
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 41% Maximum Zoom
Shear: ±0° Horizontal, ±23° Vertical
Saturation: Between -76% and +76%
Brightness: Between -39% and +39%
Exposure: Between -29% and +29%
Noise: Up to 3% of pixels