Problem with vl_nnconv while training a FCN

[omrysendik]

I am running the fcnTrain function in order to train a FCN model.
I am running it while using the VGG-16 model as the initialization (just as the script proposes).
However, when I do so, I get an error that:

Error using vl_nnconv
The number of elements of BIASES is not the same as the number of filters.

Note that the function is able to operate.
The error occurs in a specific layer in which:
size(params{1})=
1 1 4096 21
size(params{2})
1000 21

I have a feeling that it's got something to do with a lacking transpose operation.

Thanks,
Omry

[omrysendik]

I was able to find the problem and fix it by changing lines 49 to 60 in fcnInitializeModel to:

% Modify the last fully-connected layer to have 21 output classes
% Initialize the new filters to zero
Biases = 0;
for i = net.getParamIndex(net.layers(end-1).params) ;
sz = size(net.params(i).value) ;
if(~Biases)
sz(end) = 21 ;
else
sz(end-1) = 21 ;
end
net.params(i).value = zeros(sz, 'single') ;
Biases = 1;
end

[codesteller86]

@omrysendik: Thank you. it works