Dataset Versions

v5

2024-02-13 9:05am

Generated on Feb 13, 2024

Dataset Split

Train Set 91%
1245Images
Valid Set 6%
78Images
Test Set 4%
51Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1280x720
Auto-Adjust Contrast: Using Histogram Equalization
Modify Classes: 2 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -20% and +20%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 4.5px
Noise: Up to 1.49% of pixels
Cutout: 5 boxes with 15% size each

Similar Projects

See More