Dataset Versions
v3
2024-05-08 6:14pm
Generated on May 8, 2024
547 Total Images
View All Images
Dataset Split
Train Set 88%
483Images
Valid Set 7%
41Images
Test Set 4%
23Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 26% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -16% and +16%
Brightness: Between -15% and +15%