Dataset Versions

v8

2024-12-17 10:13pm

Generated on Dec 17, 2024

Dataset Split

Train Set 92%
280Images
Valid Set 5%
15Images
Test Set 3%
10Images

Preprocessing

Resize: Fit (black edges) in 640x480
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 7
Grayscale: Apply to 10% of images
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1px
Noise: Up to 0.3% of pixels