com.intel.analytics.zoo.pipeline.api.keras.layers
Int > 0. Size of the vocabulary, ie. 1 + maximum integer index occurring in the input data. Each word index in the input should be within range [0, inputDim-1].
Int > 0. Dimension of the dense embedding.
Initialization method for the weights of the layer. Default is RandomUniform. You can also pass in corresponding string representations such as 'uniform' or 'normal', etc. for simple init methods in the factory method.
Tensor. Initial weights set to this layer, which should be a Tensor of size (inputDim, outputDim). Default is null and in this case weights are initialized by the initialization method specified by 'init'. Otherwise, 'weights' will override 'init' to take effect.
Whether this layer is trainable or not. Default is true.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the embedding matrix. Default is null.
A Single Shape, does not include the batch dimension.
padding value, default 0
default true and input should be 0 based. Otherwise need to be 1 base
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
Initialization method for the weights of the layer.
Initialization method for the weights of the layer. Default is RandomUniform. You can also pass in corresponding string representations such as 'uniform' or 'normal', etc. for simple init methods in the factory method.
Tensor.
Tensor. Initial weights set to this layer, which should be a Tensor of size (inputDim, outputDim). Default is null and in this case weights are initialized by the initialization method specified by 'init'. Otherwise, 'weights' will override 'init' to take effect.
Int > 0.
Int > 0. Size of the vocabulary, ie. 1 + maximum integer index occurring in the input data. Each word index in the input should be within range [0, inputDim-1].
A Single Shape, does not include the batch dimension.
A Single Shape, does not include the batch dimension.
Int > 0.
Int > 0. Dimension of the dense embedding.
Whether this layer is trainable or not.
Whether this layer is trainable or not. Default is true.
An instance of Regularizer, (eg.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the embedding matrix. Default is null.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Turn non-negative integers (indices) into dense vectors of fixed size. The input of this layer should be 2D.
This layer can only be used as the first layer in a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
Numeric type of parameter(e.g. weight, bias). Only support float/double now.