search

frankkramer-lab / MIScnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
GNU General Public License v3.0
402 stars 116 forks source link

Multires architecture #57

Closed Jderuijter closed 3 years ago

Jderuijter commented 3 years ago

In the original paper about the MultiResUnet states: "All the convolutional layers in this network, except for the output layer, are activated by the ReLU (Rectified Linear Unit) activation function (LeCun et al., 2015), and are batch-normalized (Ioffe & Szegedy, 2015). "

So there should be no batch-normalization at the output layer. line 119: conv10 = conv2d_bn(mresblock9, n_labels, 1, 1, activation=self.activation)

suggestion: conv10 = Conv2D(n_labels, (1, 1), activation=self.activation)(mresblock9)

This problem also applies to the 3D case.

muellerdo commented 3 years ago

Hey @Jderuijter,

interesting finding!

As stated in the architecture file, the implementation was obtained directly from the main author's (Nabil Ibtehaz) GitHub repository for the MultiResUnet paper.

So, I would recommend getting in contact with the authors by opening up an issue in the paper repository:
https://github.com/nibtehaz/MultiResUNet

Cheers, Dominik