com.intel.analytics.zoo.pipeline.api.keras2.layers
Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).
One of "valid", "causal" or "same" (case-insensitive).
"valid" means "no padding".
"same" results in padding the input such that
the output has the same length as the original input.
"causal" results in causal (dilated) convolutions, e.g. output[t]
does not depend on input[t+1:]. Useful when modeling temporal data
where the model should not violate the temporal order.
Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.
Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.
Initializer for the kernel weights matrix.
Initializer for the bias vector.
Regularizer function applied to
the kernel weights matrix Default is null.
Regularizer function applied to the bias vector. Default is null.
A Single Shape, does not include the batch dimension.
Activation function to use.
Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.
Initializer for the bias vector.
Regularizer function applied to the bias vector.
Regularizer function applied to the bias vector. Default is null.
Integer, the dimensionality of the output space (i.
Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
A Single Shape, does not include the batch dimension.
A Single Shape, does not include the batch dimension.
Initializer for the kernel weights matrix.
Regularizer function applied to
the kernel weights matrix Default is null.
One of "valid", "causal" or "same" (case-insensitive).
One of "valid", "causal" or "same" (case-insensitive).
"valid" means "no padding".
"same" results in padding the input such that
the output has the same length as the original input.
"causal" results in causal (dilated) convolutions, e.g. output[t]
does not depend on input[t+1:]. Useful when modeling temporal data
where the model should not violate the temporal order.
Whether to include a bias (i.
Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
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_biasis True, a bias vector is created and added to the outputs. Finally, ifactivationis notNone, it is applied to the outputs as well.When using this layer as the first layer in a model, provide an
input_shapeargument (tuple of integers orNone, e.g.(10, 128)for sequences of 10 vectors of 128-dimensional vectors, or(None, 128)for variable-length sequences of 128-dimensional vectors.Input shape 3D tensor with shape:
(batch_size, steps, input_dim)Output shape 3D tensor with shape:
(batch_size, new_steps, filters)stepsvalue might have changed due to padding or strides.Numeric type of parameter(e.g. weight, bias). Only support float/double now.