Dataset Versions
Versions
v1
2023-07-09 10:14am
Generated on Jul 9, 2023
3146 Total Images
View All Images
Dataset Split
Train Set 84%
2649Images
Valid Set 8%
250Images
Test Set 8%
247Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Rotation: Between -5° and +5°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 25% of images
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Noise: Up to 5% of pixels