KAZAN_Merged Dataset

v1

2023-03-10 11:20pm

Generated on Mar 10, 2023

Dataset Split

Train Set 92%
10848Images
Valid Set 8%
902Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Blur: Up to 10px
Noise: Up to 5% of pixels
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Blur: Up to 10px
Bounding Box: Noise: Up to 5% of pixels