Dataset Versions
v2
2023-05-08 10:29pm
Generated on May 8, 2023
51 Total Images
View All Images
Dataset Split
Train Set 88%
45Images
Valid Set 4%
2Images
Test Set 8%
4Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 1 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 43% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±6° Horizontal, ±8° Vertical
Grayscale: Apply to 23% of images
Saturation: Between -39% and +39%
Noise: Up to 4% of pixels
Cutout: 5 boxes with 13% size each
Mosaic: Applied