Dataset Versions
v1
2024-05-23 2:45pm
Generated on May 23, 2024
377 Total Images
View All Images
Dataset Split
Train Set 88%
330Images
Valid Set 8%
32Images
Test Set 4%
15Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 48% Maximum Zoom
Rotation: Between -5° and +5°
Grayscale: Apply to 15% of images
Saturation: Between -32% and +32%
Blur: Up to 2.5px
Noise: Up to 1.76% of pixels