Dataset Versions
v2
2023-01-01 4:51am
Generated on Dec 31, 2022
834 Total Images
View All Images
Dataset Split
Train Set 85%
705Images
Valid Set 11%
91Images
Test Set 5%
38Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Brightness: Between -6% and +6%
Exposure: Between -9% and +9%
Blur: Up to 1.25px
Cutout: 3 boxes with 10% size each