Dataset Versions

v2

2023-12-27 5:28pm

Generated on Dec 27, 2023

Dataset Split

Train Set 91%
2886Images
Valid Set 6%
193Images
Test Set 3%
92Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Grayscale: Apply to 30% of images
Hue: Between -90° and +90°
Saturation: Between -34% and +34%
Exposure: Between -10% and +10%
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise