Dataset Versions
v7
2023-06-25 7:02pm
Generated on Jun 25, 2023
496 Total Images
View All Images
Dataset Split
Train Set 87%
432Images
Valid Set 8%
40Images
Test Set 5%
24Images
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
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 50% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -50% and +50%
Exposure: Between -25% and +25%
Cutout: 5 boxes with 10% size each