com.intel.analytics.zoo.pipeline.api.keras.layers
Number of convolution filters to use.
Number of rows/columns in the convolution kernel. Square kernel.
Activation function to use. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method. Default is 'tanh'.
Activation function for inner cells. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method. Default is 'hard_sigmoid'.
Format of input data. Please use "CHANNEL_FIRST" (dimOrdering='th').
Factor by which to subsample output. Also called strides elsewhere. Default is 1.
One of "same" or "valid". Also called padding elsewhere. Default is "valid".
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the input weights matrices. Default is null.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the recurrent weights matrices. Default is null.
An instance of Regularizer, applied to the bias. Default is null.
Whether to return the full sequence or the last output in the output sequence. Default is false.
Whether the input sequence will be processed backwards. Default is false.
A Single Shape, does not include the batch dimension.
Activation function to use.
Activation function to use. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method. Default is 'tanh'.
An instance of Regularizer, applied to the bias.
An instance of Regularizer, applied to the bias. Default is null.
One of "same" or "valid".
One of "same" or "valid". Also called padding elsewhere. Default is "valid".
Format of input data.
Format of input data. Please use "CHANNEL_FIRST" (dimOrdering='th').
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
Whether the input sequence will be processed backwards.
Whether the input sequence will be processed backwards. Default is false.
Activation function for inner cells.
Activation function for inner cells. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method. Default is 'hard_sigmoid'.
A Single Shape, does not include the batch dimension.
Number of rows/columns in the convolution kernel.
Number of rows/columns in the convolution kernel. Square kernel.
Number of convolution filters to use.
Whether to return the full sequence or the last output in the output sequence.
Whether to return the full sequence or the last output in the output sequence. Default is false.
Factor by which to subsample output.
Factor by which to subsample output. Also called strides elsewhere. Default is 1.
An instance of Regularizer, (eg.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the recurrent weights matrices. Default is null.
An instance of Regularizer, (eg.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the input weights matrices. Default is null.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Convolutional LSTM. Note that currently only 'same' padding is supported. The convolution kernel for this layer is a square kernel with equal strides. The input of this layer should be 5D, i.e. (samples, time, channels, rows, cols), and 'CHANNEL_FIRST' (dimOrdering='th') is expected.
When using this layer as the first layer in a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
The numeric type of parameter(e.g. weight, bias). Only support float/double now.