Main Content

clippedReluLayer

Clipped Rectified Linear Unit (ReLU) layer

expand all in page

Description

A clipped ReLU layer performs a threshold operation, where any input value less than zero is set to zero and any value above theclipping ceilingis set to that clipping ceiling.

This operation is equivalent to:

f ( x ) = { 0 , x < 0 x , 0 ≤ x < c e i l i n g c e i l i n g , x ≥ c e i l i n g .

This clipping prevents the output from becoming too large.

Creation

Syntax

layer = clippedReluLayer(ceiling)
layer = clippedReluLayer(ceiling,'Name',Name)

Description

layer=剪裁器（天花板)returns a clipped ReLU layer with the clipping ceiling equal to天花板.

example

layer=剪裁器（天花板,'Name',Name)sets the optionalNameproperty.

Properties

expand all

Clipped ReLU

用于输入剪辑的天花板，指定为正标量。

Example:10

Layer

图层名称，指定为字符向量或字符串标量。为了Layerarray input, thetrainNetwork,汇编工作,layerGraph, anddlnetworkfunctions automatically assign names to layers with name''.

Data Types:char|string

This property is read-only.

该层的输入数量。该层仅接受单个输入。

Data Types:double

This property is read-only.

Input names of the layer. This layer accepts a single input only.

Data Types:cell

This property is read-only.

Number of outputs of the layer. This layer has a single output only.

Data Types:double

This property is read-only.

Output names of the layer. This layer has a single output only.

Data Types:cell

Examples

collapse all

Open Live Script

创建一个名称的剪裁relu层'clip1'剪裁天花板等于10。

layer = clippedReluLayer(10,'Name','clip1')
layer = ClippedReLULayer with properties: Name: 'clip1' Hyperparameters Ceiling: 10

在Layerarray.

layers = [...imageInputLayer([28 28 1]) convolution2dLayer(5,20) clippedReluLayer(10) maxPooling2dLayer(2,'Stride',2) fullyConnectedLayer(10) softmaxLayer classificationLayer]
layers = 7x1 Layer array with layers: 1 '' Image Input 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' Clipped ReLU Clipped ReLU with ceiling 10 4 '' Max Pooling 2x2 max pooling with stride [2 2] and padding [0 0 0 0] 5 '' Fully Connected 10 fully connected layer 6 '' Softmax softmax 7 '' Classification Output crossentropyex

                    

                   

                  

                  

                 

                

               

              

              

               
               
              

             

            

            

             
参考

             

              
[1] Hannun, Awni, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, et al. "Deep speech: Scaling up end-to-end speech recognition." Preprint, submitted 17 Dec 2014. http://arxiv.org/abs/1412.5567

             

            

            

             
Extended Capabilities

             

              
              
              
C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

              
              
              
GPU Code Generation
使用GPU CODER™为NVIDIA®GPU生成CUDA®代码。

             

            

            

             
Version History

            

            Introduced in R2017b
            

             
See Also

             
|||

             

              
Topics