Dataset Versions
v2
2023-02-11 6:41pm
Generated on Feb 11, 2023
67 Total Images
View All Images
Dataset Split
Train Set 85%
57Images
Valid Set 9%
6Images
Test Set 6%
4Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 512x512
Augmentations
Outputs per training example: 3
Rotation: Between -9° and +9°
Grayscale: Apply to 67% of images
Brightness: Between -41% and +41%
Blur: Up to 0.5px
Noise: Up to 1% of pixels
Cutout: 3 boxes with 10% size each
Bounding Box: Crop: 0% Minimum Zoom, 59% Maximum Zoom
Bounding Box: Blur: Up to 10px