Dataset Versions
Versions
v15
2024-11-11 12:58pm
Generated on Nov 11, 2024
759 Total Images
View All Images
Dataset Split
Train Set 88%
666Images
Valid Set 9%
69Images
Test Set 3%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 416x288
Auto-Adjust Contrast: Using Contrast Stretching
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Upside Down
Crop: 0% Minimum Zoom, 23% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -34% and +34%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Noise: Up to 1.53% of pixels
Cutout: 8 boxes with 14% size each