Dataset Versions

v1

2024-03-13 4:48pm

Generated on Mar 13, 2024

Dataset Split

Train Set 87%
465Images
Valid Set 9%
50Images
Test Set 4%
21Images

Preprocessing

Auto-Orient: Applied
Static Crop: 34-81% Horizontal Region, 24-81% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Exposure: Between -12% and +12%
Blur: Up to 0.4px
Noise: Up to 1.54% of pixels

Similar Projects

See More