Dataset Versions
Versions
v1
2023-03-15 10:33am
Generated on Mar 15, 2023
653 Total Images
View All Images
Dataset Split
Train Set 92%
603Images
Valid Set 8%
50Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 38% Maximum Zoom
Rotation: Between -21° and +21°
Shear: ±24° Horizontal, ±4° Vertical
Hue: Between -129° and +129°
Saturation: Between -77% and +77%
Brightness: Between -46% and +46%
Exposure: Between -23% and +23%
Blur: Up to 1.75px
Noise: Up to 8% of pixels
Cutout: 7 boxes with 4% size each