Dataset Versions

v13

2024-09-16 12:45pm

Generated on Sep 16, 2024

Dataset Split

Train Set 87%
766Images
Valid Set 9%
83Images
Test Set 3%
27Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 1 dropped
Filter Null: Require at least 99% of images to contain annotations.

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 0.8px
Noise: Up to 0.18% of pixels