Pytorch复现U-Net, R2U-Net, Attention U-Net, Attention R2U-Net
项目地址：pytorch Implementation of U-Net, R2U-Net, Attention U-Net, Attention R2U-Net
U-Net, R2U-Net, Attention U-Net, Attention R2U-Net
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://arxiv.org/abs/1505.04597
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
https://arxiv.org/abs/1802.06955
Attention U-Net: Learning Where to Look for the Pancreas
https://arxiv.org/abs/1804.03999
Attention R2U-Net : Just integration of two recent advanced works (R2U-Net + Attention U-Net)
网络结构图
U-Net
R2U-Net
Attention U-Net
Attention R2U-Net
评估
将模型在 ISIC 2018 dataset数据集上进行测试，数据集分为训练集、验证集、测试集，占比分别为70%，10%，20%。
图片数量分别为1815，259，520.
评估指标和结果如下图所示：
来源：CSDN
作者：to_be_better_one
链接：https://blog.csdn.net/ghw15221836342/article/details/86551578