Dataset Versions

v2

2024-05-21 3:06pm

Generated on May 21, 2024

Dataset Split

Train Set 84%
208Images
Valid Set 12%
30Images
Test Set 4%
10Images

Preprocessing

Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 2
Saturation: Between -5% and +5%
Exposure: Between -5% and +5%
Bounding Box: Exposure: Between -3% and +3%
Bounding Box: Blur: Up to 1px
Bounding Box: Noise: Up to 0.15% of pixels