Dataset Versions

v5

2024-07-09 9:37am

Generated on Jul 9, 2024

Dataset Split

Train Set 92%
581Images
Valid Set 4%
28Images
Test Set 3%
22Images

Preprocessing

Auto-Orient: Applied
Static Crop: 0-100% Horizontal Region, 34-100% Vertical Region
Resize: Fit (black edges) in 640x640
Filter Null: Require at least 85% of images to contain annotations.

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical