Dataset Versions
v6
70-20-10split-augmented5x
Generated on Oct 12, 2022
3129 Total Images
View All Images
Dataset Split
Train Set 92%
2880Images
Valid Set 5%
166Images
Test Set 3%
83Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Augmentations
Outputs per training example: 5
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 35% Maximum Zoom
Rotation: Between -15° and +15°
Grayscale: Apply to 5% of images
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -25% and +25%
Blur: Up to 0.5px
Cutout: 5 boxes with 3% size each