Welcome to our Support Center
Updated

ConvLSTM1D

Description

Setup and add the convolution lstm 1D layer into the model during the definition graph step. Type : polymorphic.

 

Input parameters

 

Model in : model architecture.

Β Parameters :Β layer parameters.

Β filters :Β integer, the dimensionality of the output space.
Default value β€œ3”.
Β sizeΒ :Β integer, specify the length of the 1D convolution window.
Default value β€œ3”.
Β strideΒ :Β integer, specify the stride length of the convolution.
Default value β€œ1”.
Β explicit paddingΒ :Β array,Β specifies the number of pixels to pad at the beginning and end of each spatial axis. Batch and channel axes are not padded. Only used when padding =Β EXPLICIT.
Default value β€œempty”.
Β paddingΒ :Β enum,Β type of padding to apply.
Default value β€œVALID”.
Β ActivationΒ :Β cluster,Β activation function to use.
Β Recurrent ActivationΒ :Β cluster,Β activation function to use for the recurrent step.
Β Output ActivationΒ :Β cluster,Β activation function to use.
Β use bias? :Β boolean, whether the layer uses a bias vector.
Default value β€œTrue”.
Β Kernel InitializerΒ :Β cluster,Β initializer for theΒ kernelΒ weights matrix, used for the linear transformation of the inputs.
Β Recurrent InitializerΒ :Β cluster,Β initializer for theΒ recurrent_kernelΒ weights matrix, used for the linear transformation of the recurrent state.
Β Bias InitializerΒ :Β cluster,Β initializer for the bias vector.
Β unit forget bias? :Β boolean, If true, add 1 to the bias of the forget gate at initialization. Use in combination with Bias Initializer = ‘Zeros’.
Default value β€œTrue”.
dropout : float, between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs.
recurrent dropout : float, between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state.
Β return sequences? : boolean, Whether to return the last output in the output sequence, or the full sequence.
Default value β€œFalse”.
Β stateful? :Β boolean, if True, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch.
Default value β€œFalse”.
Β Kernel RegularizerΒ :Β cluster,Β regularizer function applied to theΒ kernelΒ weights matrix.
Β Recurrent RegularizerΒ :Β cluster,Β regularizer function applied to theΒ recurrent_kernelΒ weights matrix.
Β Bias RegularizerΒ :Β cluster,Β regularizer function applied to the bias vector.
Β training?Β :Β boolean, whether the layer is in training mode (can store data for backward).
Default value β€œTrue”.
Β store?Β :Β boolean, whether the layer stores the last iteration gradient (accessible via the β€œget_gradients” function).
Default value β€œFalse”.
Β update?Β :Β boolean, whether the layer’s variables should be updated during backward. Equivalent to freeze the layer.
Default value β€œTrue”.
Β lda coeff :Β float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value β€œ1”.

name (optional) : string, name of the layer.

 

Output parameters

 

Model out : model architecture.

Dimension

Input shape

4D tensor with shape

  • If data_format = β€˜channels_last’ : (samples, time, rows, channels).
  • If data_format = β€˜channels_first’ : (samples, time, channels, rows).

Output shape

  • if “return_sequences” = True :
    • If data_format = β€˜channels_last’ : 4D tensor with shape (samples, timesteps, new_rows, filters).
    • If data_format = β€˜channels_first’ : 4D tensor with shape (samples, timesteps, filters, new_rows).
  • if “return_sequences” = False :
    • If data_format = β€˜channels_last’ : 3D tensor with shape (samples, new_rows, filters).
    • If data_format = β€˜channels_first’ : 3D tensor with shape (samples, filters, new_rows).

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).

ConvLSTM1D layer

1 – Generate a set of data

We generate an array of data of type single and shape [samples = 10, time = 7, channels = 6, rows = 5].

2 – Define graph

First, we define the first layer of the graph which is an Input layer (explicit input layer method). This layer is setup as an input array shaped [time = 7, channels = 6, rows = 5].
Then we add to the graph the ConvLSTM1D layer.

3 – Run graph

We call the forward method and retrieve the result with the β€œPrediction 3D” method.
This method returns two variables, the first one is the layer information (cluster composed of the layer name, the graph index and the shape of the output layer) and the second one is the prediction with a shape of [samples, filters, new_rows].
The output dimension depends on the parameters β€œreturn-sequences” refer to the chapter β€œDimension” of this documentation.

 

ConvLSTM1D layer, batch and dimension

1 – Generate a set of data

We generate an array of data of type single and shape [number of batch = 9, samples = 10, time = 7, channels = 6, rows = 5].

2 – Define graph

First, we define the first layer of the graph which is an Input layer (explicit input layer method). This layer is setup as an input array shaped [time = 7, channels = 6, rows = 5].
Then we add to the graph the ConvLSTM1D layer.

3 – Run graph

We call the forward method and retrieve the result with the β€œPrediction 3D” method.
This method returns two variables, the first one is the layer information (cluster composed of the layer name, the graph index and the shape of the output layer) and the second one is the prediction with a shape of [samples, filters, new_rows].
The output dimension depends on the parameters β€œreturn-sequences” refer to the chapter β€œDimension” of this documentation.

 

Tags:
Table of Contents