Dataset Versions

v24

2024-11-08 4:08am

Generated on Nov 8, 2024

Dataset Split

Train Set 82%
348Images
Valid Set 13%
55Images
Test Set 5%
22Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 400x400
Modify Classes: 1 remapped, 1 dropped
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 2
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Shear: ±4° Horizontal, ±9° Vertical
Grayscale: Apply to 15% of images
Brightness: Between -15% and +15%
Exposure: Between -5% and +5%

Similar Projects

See More