Dataset Versions

v5

Balance-Augmentation

Generated on Jun 26, 2024

Dataset Split

Train Set 87%
5394Images
Valid Set 8%
524Images
Test Set 4%
255Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (white edges) in 1024x1024

Augmentations

Outputs per training example: 3
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.89% of pixels