Dataset Versions

v4

2023-11-15 3:03pm

Generated on Nov 15, 2023

Dataset Split

Train Set 89%
318Images
Valid Set %
0Images
Test Set 11%
40Images

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 -44% and +44%
Blur: Up to 3px