Dataset Versions

v1

2024-03-31 4:13pm

Generated on Mar 31, 2024

Dataset Split

Train Set 88%
171Images
Valid Set 8%
16Images
Test Set 4%
8Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 60% Maximum Zoom
Shear: ±43° Horizontal, ±32° Vertical
Brightness: Between -52% and +52%
Exposure: Between -10% and +10%
Blur: Up to 4px
Noise: Up to 1.68% of pixels
Mosaic: Applied
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Shear: ±10° Horizontal, ±10° Vertical
Bounding Box: Blur: Up to 4px