超音波 segmentation only bleeding Dataset
Versions
v1
2024-07-04 7:44am
Generated on Jul 4, 2024
2071 Total Images
View All Images
Dataset Split
Train Set 71%
1461Images
Valid Set 8%
169Images
Test Set 21%
441Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 320x320
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