MAIDR JavaScript API
    Preparing search index...

    Interface DirectedGraphPoint

    One node of a directed graph -- one op or layer of a computation graph.

    The edges are declared on the node they arrive at, as inputs: that is how a TensorFlow GraphDef names them (NodeDef.input) and how a Keras layer names its inbound layers, so a producer copies a field rather than inverting one. Edge order is node order, then input order -- the order the edge selectors would be in.

    Scopes are declared as a path, the way TreemapPoint.path declares a hierarchy: acyclic by construction, impossible to orphan, and already what a TensorFlow name scope is (block1/conv1/Conv2D is the path ['block1', 'conv1'] and the node Conv2D).

    { id: 'block1/add', label: 'add', path: ['block1'],
    * inputs: ['block1/conv2', 'input_1'],
    * attributes: { 'Layer type': 'Add', 'Output shape': '(None, 32, 32, 64)' } }
    interface DirectedGraphPoint {
        id: string | number;
        label?: string | number;
        path?: (string | number)[];
        inputs?: (string | number)[];
        attributes?: Record<string, string | number | boolean>;
    }
    Index

    Properties

    id: string | number

    What the other nodes' inputs name this one by. Unique in the layer.

    label?: string | number

    What the node is called when it is announced. Defaults to id.

    path?: (string | number)[]

    The scopes the node sits in, outermost first, excluding the node itself. A node at the top level omits it or declares [].

    inputs?: (string | number)[]

    The ids of the nodes feeding this one, in the order it takes them. An id naming no declared node, and a node naming itself, are ignored.

    attributes?: Record<string, string | number | boolean>

    Anything else the reader should hear about the node, announced as key, value clauses in declared order and tabulated in the description: a layer type, an output shape, a parameter count.