v1

2024-04-02 11:35am

Generated on Apr 2, 2024

Dataset Split

Train Set 88%
4176Images
Valid Set 8%
396Images
Test Set 4%
200Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Blur: Up to 2.5px
Noise: Up to 1.09% of pixels