Dataset Versions

v21

test10

Generated on Nov 2, 2023

Dataset Split

Train Set 88%
924Images
Valid Set 8%
89Images
Test Set 4%
43Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -20° and +20°
Grayscale: Apply to 40% of images
Brightness: Between -50% and +50%
Blur: Up to 4px
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down