Dataset Versions

v5

2024-07-11 10:51am

Generated on Jul 11, 2024

Dataset Split

Train Set 88%
3768Images
Valid Set 8%
360Images
Test Set 4%
178Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Grayscale: Apply to 30% of images
Brightness: Between -26% and +26%
Exposure: Between -19% and +19%
Blur: Up to 4.5px
Noise: Up to 2% of pixels

Similar Projects

See More