unpackProjectedLayers - Unpack projected layers of neural network - MATLAB (original) (raw)

Main Content

Unpack projected layers of neural network

Since R2023b

Syntax

Description

[netUnpacked](#mw%5Fba3d4854-6268-432e-8474-df9c2875eb52) = unpackProjectedLayers([net](#mw%5F54a666d6-eb49-4791-9587-0c37b8c2464e%5Fsep%5Fmw%5F3ffb42b3-6af7-4c22-82b3-4fb0f6a399f2)) replaces the layers of type ProjectedLayer with the corresponding network that represents the projection.

Examples

collapse all

Unpack Projected Layers

Load the pretrained network in dlnetProjectedJapaneseVowels.

load dlnetProjectedJapaneseVowels

View the network properties.

net = dlnetwork with properties:

     Layers: [4x1 nnet.cnn.layer.Layer]
Connections: [3x2 table]
 Learnables: [9x3 table]
      State: [2x3 table]
 InputNames: {'sequenceinput'}
OutputNames: {'softmax'}
Initialized: 1

View summary with summary.

View the network layers. The network has two projected layers.

ans = 4x1 Layer array with layers:

 1   'sequenceinput'   Sequence Input    Sequence input with 12 dimensions
 2   'lstm'            Projected Layer   Projected LSTM with 100 hidden units
 3   'fc'              Projected Layer   Projected fully connected layer with output size 9
 4   'softmax'         Softmax           softmax

Unpack the projected layers.

netUnpacked = unpackProjectedLayers(net)

netUnpacked = dlnetwork with properties:

     Layers: [5x1 nnet.cnn.layer.Layer]
Connections: [4x2 table]
 Learnables: [9x3 table]
      State: [2x3 table]
 InputNames: {'sequenceinput'}
OutputNames: {'softmax'}
Initialized: 1

View summary with summary.

View the unpacked network layers. The unpacked network has a projected LSTM layer and two fully connected layers in place of the projected layers.

ans = 5x1 Layer array with layers:

 1   'sequenceinput'   Sequence Input    Sequence input with 12 dimensions
 2   'lstm'            Projected LSTM    Projected LSTM layer with 100 hidden units, an output projector size of 7, and an input projector size of 8
 3   'fc_proj_in'      Fully Connected   4 fully connected layer
 4   'fc_proj_out'     Fully Connected   9 fully connected layer
 5   'softmax'         Softmax           softmax

Input Arguments

collapse all

net — Neural network

dlnetwork object

Neural network, specified as a dlnetwork object.

Output Arguments

collapse all

netUnpacked — Unpacked neural network

dlnetwork object

Unpacked neural network, returned as a dlnetwork object.

Tips

• Code generation does not support ProjectedLayer objects. To replace ProjectedLayer objects in a neural network with the equivalent neural network that represents the projection, use the unpackProjectedLayers function or set theUnpackProjectedLayers option of thecompressNetworkUsingProjection function to 1 (true).

Version History

Introduced in R2023b