When I try to modify the matlab provided cnn network, it says layer 11 is expected to have a different size.

Question

Lin Qi 2017-12-3

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/370699-when-i-try-to-modify-the-matlab-provided-cnn-network-it-says-layer-11-is-expected-to-have-a-differe

回答： Elizabeth Reese 2017-12-5

Here are the layer parameter.

varSize = 32;
conv1 = convolution2dLayer(5,varSize,'Padding',2,'BiasLearnRateFactor',2);
conv1.Weights = gpuArray(single(randn([5 5 3 varSize])*0.0001));
fc1 = fullyConnectedLayer(64,'BiasLearnRateFactor',2);
fc1.Weights = gpuArray(single(randn([64 576])*0.1));
fc2 = fullyConnectedLayer(4,'BiasLearnRateFactor',2);
fc2.Weights = gpuArray(single(randn([4 64])*0.1));
layers = [
    imageInputLayer([varSize varSize 3]);
    conv1;
    maxPooling2dLayer(3,'Stride',2);
    reluLayer();
    convolution2dLayer(5,32,'Padding',2,'BiasLearnRateFactor',2);
    reluLayer();
    averagePooling2dLayer(3,'Stride',2);
    convolution2dLayer(5,64,'Padding',2,'BiasLearnRateFactor',2);
    reluLayer();
    averagePooling2dLayer(3,'Stride',2);
    fc1;
    reluLayer();
    fc2;
    softmaxLayer()
    classificationLayer()];

2 个评论
显示无隐藏无

Joss Knight 2017-12-3

Please format your code correctly.

Lin Qi 2017-12-3

already did.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Elizabeth Reese 2017-12-5

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/370699-when-i-try-to-modify-the-matlab-provided-cnn-network-it-says-layer-11-is-expected-to-have-a-differe#answer_294840

When you specify the weights for fc1 and fc2, the 576 and 64 respectively is taken as the expected output size from the previous layer. You can double check that this is correct using the formulas at the bottom of the layers' documentation pages to follow through what the output size is expected to be at that point. You can test this hypothesis by removing your assignments to the weights and seeing if the network will train and what the sizes are at that stage.