NetGraph

NetGraph[{layer1, layer2, ...}, {m1 -> n1, m2 -> n2, ...}] specifies a neural net defined by a graph in which the output of layer mi is given as input to layer ni.

NetGraph[<|name1 -> layer1, name2 -> layer2, ...|>, {namem1 -> namen1, ...}] specifies a net with explicitly named layers.

NetGraph[layer] converts a layer or a NetChain into an equivalent minimal NetGraph.

Examples

net = NetGraph[
 {LinearLayer[2], ElementwiseLayer[Ramp], ThreadingLayer[Plus]},
 {1 -> 2, {NetPort["Input"], 2} -> 3}
]

Evaluating a NetGraph displays a visual preview of its layers, ports, and connections. The result remains a normal NetGraph expression and can be assigned, inspected, or used in later neural-network operations.

Something isn't working? Report an issue.

Please visit the official Wolfram Language Reference for more details.