Dataset Versions

v10

2024-12-03 11:44am

Generated on Dec 3, 2024

Dataset Split

Train Set 88%
1824Images
Valid Set 9%
180Images
Test Set 4%
80Images

Preprocessing

Auto-Orient: Applied
Static Crop: 0-100% Horizontal Region, 8-92% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 1% Minimum Zoom, 5% Maximum Zoom
Rotation: Between -15° and +15°
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Noise: Up to 0.1% of pixels