Dataset Versions

v6

2024-08-16 2:30am

Generated on Aug 16, 2024

Dataset Split

Train Set 90%
165Images
Valid Set 7%
13Images
Test Set 3%
6Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 23% of images
Saturation: Between -31% and +31%
Blur: Up to 1.8px
Noise: Up to 1.8% of pixels
Bounding Box: Blur: Up to 2.5px

Similar Projects

See More