Dataset Versions

v1

2023-10-17 4:57pm

Generated on Oct 17, 2023

Dataset Split

Train Set 88%
678Images
Valid Set 6%
48Images
Test Set 6%
47Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 16% Maximum Zoom
Grayscale: Apply to 16% of images
Hue: Between -25° and +25°
Saturation: Between -20% and +20%
Brightness: Between -25% and +25%
Noise: Up to 1% of pixels