Dataset Versions

v4

2024-10-07 4:42pm

Generated on Oct 7, 2024

Dataset Split

Train Set 89%
1248Images
Valid Set 10%
136Images
Test Set 1%
11Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Grayscale: Apply to 15% of images
Saturation: Between -32% and +32%
Brightness: Between -15% and +15%
Exposure: Between -12% and +12%
Blur: Up to 1.7px