Dataset Versions

v1

2024-08-28 2:11pm

Generated on Aug 28, 2024

Dataset Split

Train Set 87%
216Images
Valid Set 8%
20Images
Test Set 4%
11Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 47% Maximum Zoom
Rotation: Between -14° and +14°
Shear: ±15° Horizontal, ±8° Vertical
Brightness: Between -24% and +24%
Blur: Up to 2.7px
Noise: Up to 3.62% of pixels