超音波 segmentation Dataset

v3

2024-06-25 8:14am

Generated on Jun 25, 2024

Dataset Split

Train Set 70%
1416Images
Valid Set 8%
169Images
Test Set 21%
429Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Grayscale: Apply to 15% of images
Blur: Up to 1.2px
Noise: Up to 0.22% of pixels