Dataset Versions
v3
Full Data Augmentation
Generated on Nov 19, 2022
6600 Total Images
View All Images
Dataset Split
Train Set 88%
5775Images
Valid Set 8%
550Images
Test Set 4%
275Images
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, 40% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Saturation: Between -65% and +65%
Brightness: Between -40% and +40%
Exposure: Between -25% and +25%
Blur: Up to 1.5px
Noise: Up to 2% of pixels
Cutout: 3 boxes with 20% size each