[source]

GraphConvLSTM

GraphConvLSTM(output_dim, graph_conv_filters, activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)

1D convolution layer (e.g. temporal convolution).

This layer creates a convolution kernel that is convolved with the layer input over a single spatial (or temporal) dimension to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.

When using this layer as the first layer in a model, provide an input_shape argument (tuple of integers or None, e.g. (10, 128) for sequences of 10 vectors of 128-dimensional vectors, or (None, 128) for variable-length sequences of 128-dimensional vectors.

Arguments

  • output_dim: Positive integer, dimensionality of each graph node output space (or dimension of graph node embedding).
  • graph_conv_filters: 3D Tensor, the dimensionality of the output space (i.e. the number output of filters in the convolution).
  • activation: Activation function to use (see activations). If you don't specify anything, no activation is applied (ie. "linear" activation: a(x) = x).
  • use_bias: Boolean, whether the layer uses a bias vector.
  • kernel_initializer: Initializer for the kernel weights matrix (see initializers).
  • bias_initializer: Initializer for the bias vector (see initializers).
  • kernel_regularizer: Regularizer function applied to the kernel weights matrix (see regularizer).
  • bias_regularizer: Regularizer function applied to the bias vector (see regularizer).
  • activity_regularizer: Regularizer function applied to the output of the layer (its "activation"). (see regularizer).
  • kernel_constraint: Constraint function applied to the kernel matrix (see constraints).
  • bias_constraint: Constraint function applied to the bias vector (see constraints).

Input shapes

  • 4D tensor with shape: (samples, timestep, num_graph_nodes, input_dim)

Output shape

  • if return_sequences
    4D tensor with shape: (samples, timestep, num_graph_nodes, output_dim)
  • else
    4D tensor with shape: (samples, num_graph_nodes, output_dim)