twodlearn.parallel module¶
-
class
twodlearn.parallel.
ParallelLayers
(trainable=True, name=None, *args, **kwargs)[source]¶ Bases:
twodlearn.core.layers.Layer
Layer that is composed of several parallel layers.
Tdl autoinitialization with arguments:
-
input_shape
[source]¶ (
InputArgument
) Input tensor shape.
-
add
(layer)[source]¶ Add a new layer to the stacked model. The only condition is that layer must be callable.
-
build
(input_shape=None)[source]¶ Build the model. Note that this function does not build the layers.
-
compute_output_shape
(input_shape=None)[source]¶ Computes the output shape of the layer.
Assumes that the layer will be built to match that input shape provided.
- Parameters
input_shape – Shape tuple (tuple of integers) or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
- Returns
An input shape tuple.
-
input_shape
[source] Input tensor shape.
-
layers
[source] Layers that are executed sequentially.
-