Dataset Versions

v2

2024-08-26 2:28am

Generated on Aug 26, 2024

Dataset Split

Train Set 88%
3138Images
Valid Set 8%
287Images
Test Set 4%
150Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Grayscale: Apply to 100% of images
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Mosaic: Applied
Bounding Box: Blur: Up to 2.5px