Dataset Versions

v4

v4 5x F NR

Generated on Aug 28, 2023

Dataset Split

Train Set 92%
410Images
Valid Set 6%
25Images
Test Set 2%
11Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 5
Flip: Horizontal
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Grayscale: Apply to 25% of images
Hue: Between -30° and +30°
Saturation: Between -30% and +30%
Brightness: Between -25% and +25%
Exposure: Between -20% and +20%
Blur: Up to 0.5px
Noise: Up to 1% of pixels