Dataset Versions

v1

2024-11-11 1:16am

Generated on Nov 11, 2024

Dataset Split

Train Set 85%
867Images
Valid Set 11%
110Images
Test Set 4%
41Images

Preprocessing

Auto-Orient: Applied
Static Crop: 14-92% Horizontal Region, 12-77% Vertical Region
Resize: Fill (with center crop) in 550x550
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Brightness: Between -25% and +25%

Similar Projects

See More