Dataset Versions

v15

Image with issues trained from v8

Generated on Jun 22, 2024

Dataset Split

Train Set 93%
1694Images
Valid Set 5%
90Images
Test Set 2%
29Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 2000x2000
Modify Classes: 0 remapped, 1 dropped
Filter Null: Require all images to contain annotations.
Filter by Tag: 0 required, 0 dropped

Augmentations

Outputs per training example: 7
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%