v3

2023-10-12 6:48am

Generated on Oct 12, 2023

Dataset Split

Train Set 87%
306Images
Valid Set 8%
29Images
Test Set 4%
15Images

Preprocessing

Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Brightness: Between -20% and +20%
Blur: Up to 3.25px
Noise: Up to 2% of pixels