Dataset Versions

v5

2023-11-15 4:11pm

Generated on Nov 15, 2023

Dataset Split

Train Set 81%
270Images
Valid Set 4%
14Images
Test Set 15%
50Images

Preprocessing

Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 2
Flip: Horizontal
Crop: 0% Minimum Zoom, 50% Maximum Zoom
Brightness: Between 0% and +23%
Blur: Up to 3px