error while transferring weights of a trained CNN network to an empty CNN network

Question

Radians 2020-2-19

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/506387-error-while-transferring-weights-of-a-trained-cnn-network-to-an-empty-cnn-network

评论： Radians 2021-1-15

采纳的回答： Srivardhan Gadila

test1_net_original.mat

在 MATLAB Online 中打开

Hi,

I am trying to transfer the weights of layer 11 from 'original_net' to layer 11 of 'layers_final'. Both have same structure and 'layer_final' is just the empty, untrained version of 'original net'. i am using the following command:

Layers_final(11).Weights = net_1.Layers(11).Weights

I get the following error while doing so:

Error using nnet.cnn.layer.TransposedConvolution2DLayer/set.Weights (line 204)

Expected input to be of size 4x4x8x1, but it is of size 4x4x8x8.

code for layers_final:

imageLayer_final = imageInputLayer([32,32,1]);
encodingLayers_final = [ ...
    convolution2dLayer(3,16,'Padding','same'), ...
    reluLayer, ...
    maxPooling2dLayer(2,'Padding','same','Stride',2), ...
    convolution2dLayer(3,8,'Padding','same'), ...
    reluLayer, ...
    maxPooling2dLayer(2,'Padding','same','Stride',2), ...
    convolution2dLayer(3,8,'Padding','same'), ...
    reluLayer, ...
    maxPooling2dLayer(2,'Padding','same','Stride',2)];
decodingLayers_final = [ ...
    createUpsampleTransponseConvLayer(2,8), ...
    reluLayer, ...
    createUpsampleTransponseConvLayer(2,8), ...
    reluLayer, ...
    createUpsampleTransponseConvLayer(2,16), ...
    reluLayer, ...
    convolution2dLayer(3,1,'Padding','same'), ...
    clippedReluLayer(1.0), ...
    regressionLayer];
layers_final = [imageLayer,encodingLayers,decodingLayers];

net_original attached with the question.

Thanks

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Srivardhan Gadila 2020-2-24

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/506387-error-while-transferring-weights-of-a-trained-cnn-network-to-an-empty-cnn-network#answer_417066

在 MATLAB Online 中打开

If the function createUpsampleTransponseConvLayer is the helper function from the example Prepare Datastore for Image-to-Image Regression then change the 'NumChannels' Name-Value Pair Argument to 'auto' or don't mention it in the transposedConv2dLayer function.

% helper function from the example Prepare Datastore for Image-to-Image Regression
function out = createUpsampleTransponseConvLayer(factor,numFilters)
filterSize = 2*factor - mod(factor,2); 
cropping = (factor-mod(factor,2))/2;
numChannels = 1;
out = transposedConv2dLayer(filterSize,numFilters, ... 
    'NumChannels',numChannels,'Stride',factor,'Cropping',cropping);
end

Since the layer is defined with 'NumChannels' (number of channels of the input to this transposedConv2dLayer) as 1 hence it can accept wieghts of size "filterSize x filterSize x numFilters x numChannels" which is 4x4x8x1 in this case.

Change the function as follows:

function out = createUpsampleTransponseConvLayer(factor,numFilters)
filterSize = 2*factor - mod(factor,2); 
cropping = (factor-mod(factor,2))/2;
out = transposedConv2dLayer(filterSize,numFilters, ... 
    'Stride',factor,'Cropping',cropping);
end

and then define the layers.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Srivardhan Gadila 2020-3-9

I have heard that this issue is known and the concerned parties might be working on it.

Radians 2021-1-15

Hello

I know its been long now but if I try to perform the same operation with the transpose convolution function as follows:

O_dltconv1=dltranspconv(O_maxpool3,K_tconv_1,B_tconv_1,'Stride',2,'Cropping',1);

with:

K>> size(O_maxpool3)

ans =

4 4 8 500

K>> size(K_tconv_1)

ans =

4 4 8

K>> size(B_tconv_1)

ans =

1 1 8

I get the following error:

Number of channels to convolve (1, specified by the size of the 'U' dimension of the weights) must be equal

to the size of the 'C' dimension of the input data (8).

Could you please highlight what am I doing wrong, since I set the channels of the transpose convolution filter to 1 as you said?

请先登录，再进行评论。

error while transferring weights of a trained CNN network to an empty CNN network

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

3 个评论
显示 1更早的评论隐藏 1更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

error while transferring weights of a trained CNN network to an empty CNN network

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

3 个评论 显示 1更早的评论隐藏 1更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

WeChat

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

3 个评论
显示 1更早的评论隐藏 1更早的评论