Dataset Versions
v3
2024-11-26 4:40pm
Generated on Nov 26, 2024
975 Total Images
View All Images
Dataset Split
Train Set 87%
852Images
Valid Set 8%
82Images
Test Set 4%
41Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±5° Horizontal, ±5° Vertical
Saturation: Between -2% and +2%
Brightness: Between -5% and +5%
Exposure: Between -2% and +2%
Blur: Up to 0.5px
Noise: Up to 0.1% of pixels