Dataset Versions

v1

2023-12-23 12:24am

Generated on Dec 22, 2023

Dataset Split

Train Set 87%
501Images
Valid Set 8%
47Images
Test Set 4%
25Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 485x860
Auto-Adjust Contrast: Using Histogram Equalization
Grayscale: Applied

Augmentations

Outputs per training example: 3
Grayscale: Apply to 48% of images
Hue: Between -50° and +50°
Saturation: Between -50% and +50%
Brightness: Between 0% and +33%
Exposure: Between -3% and +3%
Blur: Up to 1.5px
Noise: Up to 20% of pixels
Mosaic: Applied