Dataset Versions
v1
2023-07-11 10:39pm
Generated on Jul 12, 2023
227 Total Images
View All Images
Dataset Split
Train Set 85%
192Images
Valid Set 11%
25Images
Test Set 4%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Shear: ±45° Horizontal, ±0° Vertical
Grayscale: Apply to 100% of images
Saturation: Between -99% and +99%
Exposure: Between -42% and +42%
Blur: Up to 2.75px
Cutout: 25 boxes with 11% size each
Mosaic: Applied
Bounding Box: Crop: 0% Minimum Zoom, 36% Maximum Zoom