Dataset Versions
v4
2023-01-05 10:19pm
Generated on Jan 5, 2023
675 Total Images
View All Images
Dataset Split
Train Set 88%
591Images
Valid Set 8%
56Images
Test Set 4%
28Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 23% Maximum Zoom
Rotation: Between -14° and +14°
Hue: Between -76° and +76°
Brightness: Between -38% and +38%
Blur: Up to 2.25px
Noise: Up to 7% of pixels
Cutout: 10 boxes with 5% size each
Mosaic: Applied
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise