torch - Torch7, how to calculate the number of parameters in a convNet -

i looking way calculate number of parameters in convolutional neural network. in particular, using resnet model in https://github.com/facebook/fb.resnet.torch. know if there function calculate total number of parameters? have other suggestion doing it? in advance.

you have go through each layer of network , count number of parameters in layer. here sample function that:

-- example model fed function model = nn.sequential() model:add(nn.spatialconvolution(3,12,1,1)) model:add(nn.linear(2,3)) model:add(nn.relu())  function countparameters(model) local n_parameters = 0 i=1, model:size()    local params = model:get(i):parameters()    if params      local weights = params[1]      local biases  = params[2]      n_parameters  = n_parameters + weights:nelement() + biases:nelement()    end end return n_parameters end