Dataset Versions

v1

2023-09-30 7:56pm

Generated on Sep 30, 2023

Dataset Split

Train Set 87%
3366Images
Valid Set 8%
321Images
Test Set 4%
160Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Grayscale: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 14% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 2.5px
Noise: Up to 5% of pixels