jlcsilva / EfficientUNetPlusPlus

Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.

https://arxiv.org/abs/2106.11447

Predicted error reporting

mmliu202210 opened this issue a year ago · comments

mmliu202210 commented a year ago

Hello ! Sir !
There are always a lot of fractures in the predicted results. Is there any post-treatment process? Look forward to your guidance!