layerGraph — Create a layer graph compatibility object.
layerGraph creates a host metadata graph object from zero inputs or a layer collection.
Syntax
graph = layerGraph
graph = layerGraph(layers)How layerGraph works
- Accepts zero inputs, a layer object, a cell array of layer objects, or an object list.
- Stores
Layers,LayerNames, and an emptyConnectionsstructure. - Connection editing helpers such as
addLayersandconnectLayersremain outside this slice.
GPU memory and residency
Layer graph construction is host metadata work and has no provider kernel.
Example
Create Graph From Layers
layers = {featureInputLayer(4,'Name','in'); fullyConnectedLayer(2,'Name','fc')};
graph = layerGraph(layers)Expected output:
Layer graph compatibility object.Using layerGraph with coding agents
Open a RunMat example with live inputs, then ask the agent to explain how layerGraph changes the result.
Run a small layerGraph example, explain the result, then change one input and compare the output.
Related Deep Learning functions
adamupdate · analyzeNetwork · bilstmLayer · classificationLayer · combvec · convolution1dLayer · crossentropy · dlarray · dlfeval · dlgradient · dlnetwork · dlupdate · eluLayer · exportONNXNetwork · featureInputLayer · forward · fullyConnectedLayer · globalAveragePooling1dLayer · layerNormalizationLayer · lstmLayer · padsequences · regressionLayer · reluLayer · sequenceInputLayer · softmaxLayer · trainingOptions · trainnet · trainNetwork
About RunMat
RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.
- RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
- Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.