是否需要在caffe的deploy.prototxt中定义退出层？

问题描述

在caffe的AlexNet实现中，我在deploy.prototxt文件中看到以下层：

In the AlexNet implementation in caffe, I saw the following layer in the deploy.prototxt file:

layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}

现在，退出的关键思想是随机删除单位（以及

Now the key idea of dropout is to randomly drop units (along with their connections) from the neural network during training.

这是否意味着我可以简单地从deploy.prototxt中删除该层，因为该文件将在测试期间使用只要？

Does this mean that I can simply delete this layer from deploy.prototxt, as this file is meant to be used during testing only?

推荐答案

是。在测试过程中不需要退出。

Yes. Dropout is not required during Testing.

即使您包括一个退出层，在测试过程中也不会发生任何特殊情况。请参见辍学前向通行证的源代码：

Even if you include a dropout layer, nothing special happens during Testing. See the source code of dropout forward pass:

  if (this->phase_ == TRAIN) {
    // Code to do something
  } else {
    caffe_copy(bottom[0]->count(), bottom_data, top_data);  //Code to copy bottom blob to top blob
  }

如源代码所示，如果底部Blob数据不在训练阶段，则会将其复制到顶部Blob数据存储器中。

As seen in the source code, the bottom blob data is copied to top blob data memory if its not on Training phase.

这篇关于是否需要在caffe的deploy.prototxt中定义退出层？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！