Dataset Versions

v4

2024-07-08 3:29pm

Generated on Jul 8, 2024

Dataset Split

Train Set 93%
621Images
Valid Set 4%
26Images
Test Set 3%
23Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require at least 80% of images to contain annotations.

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical