Dataset Versions

v5

2024-06-02 12:38am

Generated on Jun 1, 2024

Dataset Split

Train Set 88%
3381Images
Valid Set 8%
323Images
Test Set 4%
160Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-70% Horizontal Region, 25-70% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Blur: Up to 1px
Noise: Up to 1.84% of pixels

Similar Projects

See More