Dataset Versions
v2
2nd augmentation
Generated on Sep 5, 2023
329 Total Images
View All Images
Dataset Split
Train Set 88%
288Images
Valid Set 6%
20Images
Test Set 6%
21Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 10% Minimum Zoom, 29% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±21° Horizontal, ±21° Vertical
Grayscale: Apply to 100% of images
Hue: Between -135° and +135°
Saturation: Between -55% and +55%
Brightness: Between -50% and +50%
Exposure: Between -15% and +15%
Noise: Up to 10% of pixels