Detecting Oral Diseaese Dataset

v1

2024-07-11 7:09pm

Generated on Jul 11, 2024

Dataset Split

Train Set 87%
5001Images
Valid Set 8%
477Images
Test Set 4%
238Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-72% Horizontal Region, 19-56% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°