classification project Dataset

v3

2024-06-01 10:51pm

Generated on Jun 1, 2024

Dataset Split

Train Set 90%
27Images
Valid Set 7%
2Images
Test Set 3%
1Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-65% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 1000x1000
Grayscale: Applied

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Blur: Up to 1px
Cutout: 3 boxes with 13% size each