Dataset Versions

v2

2024-09-18 1:20pm

Generated on Sep 18, 2024

Dataset Split

Train Set 88%
138Images
Valid Set 8%
13Images
Test Set 4%
6Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 640x480

Augmentations

Outputs per training example: 3
Grayscale: Apply to 17% of images
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels