Dataset Versions
v5
2024-10-25 12:20pm
Generated on Oct 25, 2024
306 Total Images
View All Images
Dataset Split
Train Set 94%
287Images
Valid Set 5%
14Images
Test Set 2%
5Images
Preprocessing
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 7
Crop: 0% Minimum Zoom, 1% Maximum Zoom
Rotation: Between -2° and +2°
Brightness: Between -2% and +2%
Exposure: Between -4% and +4%
Noise: Up to 0.02% of pixels
Bounding Box: Shear: ±1° Horizontal, ±3° Vertical