Dataset Versions
v2
2024-07-25 5:17pm
Generated on Jul 25, 2024
321 Total Images
View All Images
Dataset Split
Train Set 88%
282Images
Valid Set 8%
26Images
Test Set 4%
13Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -24° and +24°
Saturation: Between -25% and +25%
Exposure: Between -13% and +13%
Noise: Up to 0.1% of pixels