ConvolutionLayer - Maple Help
For the best experience, we recommend viewing online help using Google Chrome or Microsoft Edge.

Online Help

All Products    Maple    MapleSim


DeepLearning

  

ConvolutionLayer

  

create convolution layer

  

DeconvolutionLayer

  

create deconvolution layer

 

Calling Sequence

Parameters

Options

Description

Details

Examples

Compatibility

Calling Sequence

ConvolutionLayer(filters,kernelsize,opts)

DeconvolutionLayer(filters,kernelsize,opts)

Parameters

filter

-

positive integer

kernelsize

-

list of positive integers

opts

-

(optional) one or more keyword options described below

Options

• 

inputshape : list of integers or the symbol auto

  

Shape of the input Tensor, not including the batch axis.

  

With the default value auto, the shape is inferred. If inference is not possible, an error is issued.

  

This option need only be specified when this layer is the first in a Sequential model.

Description

• 

ConvolutionLayer(filters,kernelsize,opts) creates a convolutional neural network layer with filter filter and kernel size kernelsize.

• 

DeconvolutionLayer(filters,kernelsize,opts) creates a deconvolutional neural network layer with filter filter and kernel size kernelsize.

• 

This function is part of the DeepLearning package, so it can be used in the short form Convolution(..) only after executing the command with(DeepLearning). However, it can always be accessed through the long form of the command by using DeepLearning[ConvolutionLayer](..).

Details

• 

The implementation of ConvolutionLayer uses tf.keras.layers.Conv1D, tf.keras.layers.Conv2D, and tf.keras.layers.Conv3D from the TensorFlow Python API.

• 

The implementation of DeconvolutionLayer uses tf.keras.layers.Conv1DTranspose, tf.keras.layers.Conv2DConv1DTranspose, and tf.keras.layers.Conv3DConv1DTranspose from the TensorFlow Python API.

• 

Consult the TensorFlow Python API documentation for tf.keras.layers for more information.

Examples

withDeepLearning

AddMultiple,ApplyOperation,BatchNormalizationLayer,BidirectionalLayer,BucketizedColumn,CategoricalColumn,Classify,Concatenate,Constant,ConvolutionLayer,DNNClassifier,DNNLinearCombinedClassifier,DNNLinearCombinedRegressor,DNNRegressor,Dataset,DenseLayer,DropoutLayer,EinsteinSummation,EmbeddingLayer,Estimator,FeatureColumn,Fill,FlattenLayer,GRULayer,GatedRecurrentUnitLayer,GetDefaultGraph,GetDefaultSession,GetEagerExecution,GetVariable,GradientTape,IdentityMatrix,LSTMLayer,Layer,LinearClassifier,LinearRegressor,LongShortTermMemoryLayer,MaxPoolingLayer,Model,NumericColumn,OneHot,Ones,Operation,Optimizer,Placeholder,RandomTensor,ResetDefaultGraph,Restore,Save,Sequential,Session,SetEagerExecution,SetRandomSeed,SoftMaxLayer,SoftmaxLayer,Tensor,Variable,Variables,VariablesInitializer,Zeros

(1)

modelSequentialConvolutionLayer2,3,activation=relu

modelDeepLearning Model<keras.engine.sequential.Sequential object at 0x7fa544e2ae30>

(2)

model:-Compile

Compatibility

• 

The DeepLearning[ConvolutionLayer] and DeepLearning[DeconvolutionLayer] commands were introduced in Maple 2021.

• 

For more information on Maple 2021 changes, see Updates in Maple 2021.

See Also

DeepLearning Overview