Dataset Versions
v1
2024-12-18 7:33pm
Generated on Dec 18, 2024
611 Total Images
View All Images
Dataset Split
Train Set 97%
590Images
Valid Set 3%
16Images
Test Set 1%
5Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 200x200
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 10
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 50% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±45° Horizontal, ±45° Vertical
Saturation: Between -83% and +83%
Brightness: Between -41% and +41%
Exposure: Between -11% and +11%
Blur: Up to 5.5px
Noise: Up to 10% of pixels
Cutout: 25 boxes with 4% size each