Dataset Versions
v2
2024-02-04 9:30pm
Generated on Feb 4, 2024
76 Total Images
View All Images
Dataset Split
Train Set 91%
69Images
Valid Set 8%
6Images
Test Set 1%
1Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Upside Down
Crop: 0% Minimum Zoom, 6% Maximum Zoom
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Brightness: Between -23% and +23%