MATLAB: How to see the output of the maxpooling layer

cnnconvolutional neural network

Hi! Is there a way to see the outputs of my Layers in Convolutional Neural Network.

So to start off, I created a Convolutional Neural Network and I want to see the outputs for each Layers. For example, I have my maxPooling2dLayer and I want to know how many feature maps it produced and what are the values of each feature maps.

Best Answer

Have you tried using this features = activations(network,input ,layer number)

Specify the network name, your input which would be an image or a feature map, and the number of the layer you whose output you want to check for example 2 for the second layer.

Related Solutions

MATLAB: Error when using convolution2dLayer between connected maxPooling2dLayer and maxUnpooling2dLayer

You convolution layer is changing the number of channels in the output after the max pooling.

This causes the input size mismatch. You need to match the number of channels output by convolution layer to the output by maxpooling layer.

% define layers
layers = [
    imageInputLayer([128, 128], 'Name', 'INPUTLAYER')
    maxPooling2dLayer([2 2], 'HasUnpoolingOutputs', true, 'Stride', [2 2], 'Name', 'MAXPOOL')
    convolution2dLayer([3 3], 1, 'Padding', 'same', 'Stride', [1 1], 'Name', 'CONV')
    maxUnpooling2dLayer('Name', 'UNPOOL')
    regressionLayer('Name', 'MSE')
    ]; 
% define network
lgraph = layerGraph(layers);
% define connections
lgraph = connectLayers(lgraph, 'MAXPOOL/indices', 'UNPOOL/indices');
lgraph = connectLayers(lgraph, 'MAXPOOL/size', 'UNPOOL/size');
% plot and check
analyzeNetwork(lgraph);

MATLAB: Modifying unetLayers-architecture for distance map regression

In addition to above replace the 'Final-ConvolutionLayer' with new convolution2dLayer having filter size 1 and number of filters 1 as follows:

imageSize = [128 128 1];
numClasses = 2;
encoderDepth = 4;
lgraph = unetLayers(imageSize,numClasses,'EncoderDepth',encoderDepth);
lgraph = replaceLayer(lgraph,'Final-ConvolutionLayer',convolution2dLayer(1,1,'Name','Final-ConvolutionLayer'));
lgraph = replaceLayer(lgraph,'Segmentation-Layer',regressionLayer('name','regressionLayer'));
lgraph = removeLayers(lgraph, 'Softmax-Layer'); 
lgraph = lgraph.connectLayers('Final-ConvolutionLayer', 'regressionLayer');
analyzeNetwork(lgraph)

Best Answer

Related Solutions

MATLAB: Error when using convolution2dLayer between connected maxPooling2dLayer and maxUnpooling2dLayer

MATLAB: Modifying unetLayers-architecture for distance map regression

Related Question