Dataset Versions
v1
2023-11-03 1:30pm
Generated on Nov 3, 2023
748 Total Images
View All Images
Dataset Split
Train Set 87%
654Images
Valid Set 8%
62Images
Test Set 4%
32Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 28% Maximum Zoom
Hue: Between -177° and +177°
Saturation: Between -92% and +92%
Blur: Up to 4.75px
Noise: Up to 15% of pixels
Cutout: 13 boxes with 14% size each