Dataset Versions

v7

2024-12-04 3:47am

Generated on Dec 3, 2024

Dataset Split

Train Set 95%
3230Images
Valid Set 3%
90Images
Test Set 2%
84Images

Preprocessing

Auto-Orient: Applied
Static Crop: 38-78% Horizontal Region, 37-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 5
Flip: Horizontal
Grayscale: Apply to 10% of images
Hue: Between -8° and +8°
Saturation: Between -22% and +22%
Exposure: Between -10% and +10%
Noise: Up to 1.34% of pixels

Similar Projects

See More