unity3d-unet - Why does the order in the upsampling path of the U-Net developed by Monai deviate from standard u-net?
问题描述
I have a question about the U-Net developed by @monai. They refer to this link: https://link.springer.com/chapter/10.1007/978-3-030-12029-0_40. for explanation about the residual units they use. In every layer of their upsampling path, they first apply a transposed convolution, then a 'normal' convolution and then they concatanate the result with the result of the same layer of the downsampling path. However, in the link they refer to, the order is transposed convolution --> concatenation --> normal convolution. Does anyone know why they deviate from this usual order, and does the order have any influence on the result?
Thanks in advance!
解决方案
推荐阅读
- javascript - 连字符比较 -
- node.js - 'err' 已在上层范围内声明
- c# - 无法通过命令行参数将 ApplicationVersion 传递给 MSBuild
- javascript - 获取 ReferenceError: (token) is not defined JavaScript Discord
- asp.net-core-2.2 - 在 .net core 2.2 中引用 .net(4.7.1) 项目
- python - 在 Python 中更改 For 循环的索引(在 if 语句之外)
- linux - 如何在 ubuntu 上从源代码安装 postgres?
- r - R中的双for循环问题
- linux - 如何使用 SED 命令查找和替换文件路径(以及特殊字符)
- java - 为什么 Log4j2 Appenders 不将下一行中的第一个日志添加到标题中?