For example, list(4L, 20L) -> list(c(0.25, 0.1), c(0.6, -0.2)) This layer
can only be used as the first layer in a model.
layer_embedding(object, input_dim, output_dim,
embeddings_initializer = "uniform", embeddings_regularizer = NULL,
activity_regularizer = NULL, embeddings_constraint = NULL,
mask_zero = FALSE, input_length = NULL, batch_size = NULL,
name = NULL, trainable = NULL, weights = NULL)Model or layer object
int > 0. Size of the vocabulary, i.e. maximum integer index + 1.
int >= 0. Dimension of the dense embedding.
Initializer for the embeddings matrix.
Regularizer function applied to the
embeddings matrix.
activity_regularizer
Constraint function applied to the embeddings
matrix.
Whether or not the input value 0 is a special "padding"
value that should be masked out. This is useful when using recurrent
layers, which may take variable length inputs. If this is TRUE then all
subsequent layers in the model need to support masking or an exception will
be raised. If mask_zero is set to TRUE, as a consequence, index 0 cannot be
used in the vocabulary (input_dim should equal size of vocabulary + 1).
Length of input sequences, when it is constant. This
argument is required if you are going to connect Flatten then Dense
layers upstream (without it, the shape of the dense outputs cannot be
computed).
Fixed batch size for layer
An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided.
Whether the layer weights will be updated during training.
Initial weights for layer.
2D tensor with shape: (batch_size, sequence_length).
3D tensor with shape: (batch_size, sequence_length, output_dim).