layerGraph
深度学习的网络层图
Description
A layer graph specifies the architecture of a deep learning network with a more complex graph structure in which layers can have inputs from multiple layers and outputs to multiple layers. Networks with this structure are called directed acyclic graph (DAG) networks. After you create alayerGraph
object, you can use the object functions to plot the graph and modify it by adding, removing, connecting, and disconnecting layers. To train the network, use the layer graph as input to thetrainNetwork
function or convert it to adlnetwork
and train it using a custom training loop.
Creation
Description
creates an empty layer graph that contains no layers. You can add layers to the empty graph by using thelgraph
= layergraphaddLayers
function.
creates a layer graph from an array of network layers and sets thelgraph
= layergraph(layers
)Layers
property. The layers inlgraph
are connected in the same sequential order as inlayers
.
Input Arguments
Properties
Object Functions
addLayers |
Add layers to layer graph |
removeLayers |
Remove layers from layer graph |
replaceLayer |
Replace layer in layer graph |
connectLayers |
Connect layers in layer graph |
disconnectLayers |
Disconnect layers in layer graph |
plot |
Plot neural network layer graph |