tfmot.quantization.keras.graph_transformations.transforms.LayerNode

Represents a Node in a tree containing a layer.

tfmot.quantization.keras.graph_transformations.transforms.LayerNode(
    layer,
    weights=None,
    input_layers=None,
    metadata=None,
    names_and_weights=None
)

LayerNode is used to represent a tree of layers in a model. It contains config which describes the layer, and other input layers feeding into it.

It is used as a generic class to represent both sets of layers which have been found in a model, and layers which should be replaced inside the model.

layer layer config of this node.
weights An OrderedDict of weight name => value for the layer.
input_layers List of LayerNodes that feed into this layer.
metadata Dictionary of metadata for a given layer.
names_and_weights A list of tuples (name, weight). It only used when weights dictionary is empty.

Methods

__eq__

View source

__eq__(
    other
)

Return self==value.

__ne__

View source

__ne__(
    other
)

Ensure this works on Python2.