isequal

Check equality of neural networks

Since R2021a

Syntax

tf = isequal(net1,net2)

tf = isequal(net1,...,netN)

Description

tf = isequal(net1,net2) checks the equality of dlnetwork objects net1 and net2. The function returns 1 (true) when the properties and architectures match. Otherwise, the function returns 0 (false).

The isequal function can operate on arrays of networks. In this case, the function performs element-wise comparison.

tf = isequal(net1,...,netN) checks equality of the N networks net1, …, netN.

Examples

Check if Networks are Equal

Create two instances of a pretrained SqueezeNet network.

net1 = imagePretrainedNetwork;
net2 = imagePretrainedNetwork;

Check if the networks are equal using the isequal function.

tf = isequal(net1,net2)

tf = logical
   1

Input Arguments

net1,net2 — Neural networks

dlnetwork object

Neural networks, specified as dlnetwork objects.

Version History

Introduced in R2021a

R2024a: SeriesNetwork, DAGNetwork, and LayerGraph objects are not recommended

Starting in R2024a, SeriesNetwork, DAGNetwork, and LayerGraph objects are not recommended. Use dlnetwork objects instead. This recommendation means that SeriesNetwork, DAGNetwork, and LayerGraph input to the isequal function is not recommended.

For SeriesNetwork, DAGNetwork, and LayerGraph, the isequal function has this behavior:

• If both inputs are SeriesNetwork or DAGNetwork objects, or one of each, then the function returns 1 (true) when the properties and architectures match. Otherwise, the function returns 0 (false).

• If both inputs are LayerGraph objects, then the function returns 1 (true) when the properties and architectures match. Otherwise, the function returns 0 (false).

• For other combinations, the function returns 0 (false).

Most functions that support LayerGraph objects also support dlnetwork objects. This table shows some typical usages of LayerGraph objects and how to update your code to use dlnetwork object functions instead.

Not Recommended	Recommended
lgraph = layerGraph;	net = dlnetwork;
lgraph = layerGraph(layers);	net = dlnetwork(layers,Initialize=false);
lgraph = layerGraph(net);	net = dag2dlnetwork(net);
lgraph = addLayers(lgraph,layers);	net = addLayers(net,layers);
lgraph = removeLayers(lgraph,layerNames);	net = removeLayers(net,layerNames);
lgraph = replaceLayer(lgraph,layerName,layers);	net = replaceLayer(net,layerName,layers);
lgraph = connectLayers(lgraph,s,d);	net = connectLayers(net,s,d);
lgraph = disconnectLayers(lgraph,s,d);	net = disconnectLayers(net,s,d);
plot(lgraph);	plot(net);

To train a neural network specified as a dlnetwork object, use the trainnet function.