Dataset Versions

v8

2024-12-12 1:27pm

Generated on Dec 12, 2024

Dataset Split

Train Set 92%
120Images
Valid Set 5%
6Images
Test Set 3%
4Images

Preprocessing

Resize: Fit within 640x640
Filter Null: Do not filter any null images.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -32° and +32°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -22° and +22°
Noise: Up to 1.65% of pixels