how to convert this block of code to python?

%convert the weights to -1 and + 1. Store in single because conv2 requires it
for i = 1:length(Filters)
    Filters{i} = gpuArray(2*(single(sign(Filters{i}))-0.5));
    NumLearntWeightsEachLayer(i) = size(Filters{i},3)*size(Filters{i},4)*4;
end
NumLearntWeightsEachLayer(end) = size(Filters{end},3)*size(Filters{end},4);
NumLearntWeightsEachLayer
TotalLearntWeights = sum(NumLearntWeightsEachLayer)

[Prb]

any leads on the topic would be appreciated. Thanks

[Walter Roberson]

https://devblogs.nvidia.com/numba-python-cuda-acceleration/

[Prb]

I would like to have something similar problem solved as a lead to my question.

[Walter Roberson]

https://stackoverflow.com/questions/40609838/what-is-the-equivalent-to-a-matlab-cell-array

Answer 1

[Prb]

I think this is the right answer here

for i in range (0,len(Filters)):

for j in range(0, len(Filters[i]):

Filters[i][j] = (2*(Filters[i][j] - 0.5))

NumLearntWeightsEachLayer[i] = len(Filters[i][3])*len(Filters[i][4])*4

NumLearntWeightsEachLayer[-1] = len(Filters[-1][3])*len(Filters[-1][4])

print NumLearntWeightsEachLayer

TotalLearntWeights = sum(NumLearntWeightsEachLayer)