Dataset Versions
v3
2023-11-12 2:28pm
Generated on Nov 12, 2023
346 Total Images
View All Images
Dataset Split
Train Set 88%
303Images
Valid Set 8%
29Images
Test Set 4%
14Images
Preprocessing
Auto-Orient: Applied
Filter Null: Require at least 29% of images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical