Dataset Versions

v4

wet_augment

Generated on Oct 19, 2023

Dataset Split

Train Set 83%
48Images
Valid Set 9%
5Images
Test Set 9%
5Images

Preprocessing

Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 17% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Brightness: Between -21% and +21%
Noise: Up to 5% of pixels
Mosaic: Applied