Dataset Versions

v18

2023-09-22 11:22am

Generated on Sep 22, 2023

Dataset Split

Train Set 87%
750Images
Valid Set 8%
71Images
Test Set 5%
39Images

Preprocessing

Resize: Fit (black edges) in 1280x1280
Modify Classes: 22 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 99% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±45° Horizontal, ±45° Vertical
Hue: Between -90° and +90°
Saturation: Between -50% and +50%
Brightness: Between -50% and +50%
Exposure: Between -50% and +50%
Blur: Up to 5px
Noise: Up to 10% of pixels
Cutout: 10 boxes with 10% size each
Mosaic: Applied

Similar Projects

See More