Dataset Versions
v4
2022-05-15 10:22pm
Generated on May 16, 2022
202 Total Images
View All Images
Dataset Split
Train Set 65%
132Images
Valid Set 20%
41Images
Test Set 14%
29Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white edges) in 416x416
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 46% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±15° Horizontal, ±15° Vertical
Mosaic: Applied