com.intel.analytics.zoo.pipeline.api.keras.layers
Int > 0. Size of the vocabulary.
Int >= 0. Dimension of the dense embedding.
A string specifying the reduce type. Currently "mean", "sum", "sqrtn" is supported.
If provided, each embedding is normalized to have l2 norm equal to maxNorm before combining.
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.
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.
A string specifying the reduce type.
A string specifying the reduce type. Currently "mean", "sum", "sqrtn" is supported.
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.
Int > 0.
Int > 0. Size of the vocabulary.
A Single Shape, does not include the batch dimension.
If provided, each embedding is normalized to have l2 norm equal to maxNorm before combining.
Int >= 0.
Int >= 0. Dimension of the dense embedding.
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)
SparseEmbedding is the sparse version of layer Embedding.
The input of SparseEmbedding should be a 2D SparseTensor or two 2D sparseTensors. If the input is a SparseTensor, the values are positive integer ids, values in each row of this SparseTensor will be turned into a dense vector. If the input is two SparseTensors, the first tensor should be the integer ids, just like the SparseTensor input. And the second tensor is the corresponding weights of the integer ids.
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.