MATLAB neural network pattern recognition

I created a simple neural network for recognizing mouse gestures (inputs are angles), and I used nprtool (function patternnet to create). I saved the weights and offsets of the network:

W1=net.IW{1,1};
W2=net.LW{2,1};
b1=net.b{1,1};
b2=net.b{2,1};

and to calculate the result, I used tansig(W2*(tansig(W1*in+b1))+b2); where in- the input. But the result is terrible (each number is approximately 0.99). The result from commend net(in)is good. What am I doing wrong? It is very important for me why the first method is bad (I do the same in my C ++ program). I ask for help :)

[edit] The code below was created from nprtool GUI. It might be useful to someone, but I don't see any solution to my problem from this code. For hidden and output levels of neurons, the tansig activation function is used (is there any parameter in the MATLAB network?).

% Solve a Pattern Recognition Problem with a Neural Network
% Script generated by NPRTOOL
% Created Tue May 22 22:05:57 CEST 2012
%
% This script assumes these variables are defined:
%
%   input - input data.
%   target - target data.    
inputs = input;
targets = target;

% Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);

% Choose Input and Output Pre/Post-Processing Functions
% For a list of all processing functions type: help nnprocess
net.inputs{1}.processFcns = {'removeconstantrows','mapminmax'};
net.outputs{2}.processFcns = {'removeconstantrows','mapminmax'};


% Setup Division of Data for Training, Validation, Testing
% For a list of all data division functions type: help nndivide
net.divideFcn = 'dividerand';  % Divide data randomly
net.divideMode = 'sample';  % Divide up every sample
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

% For help on training function 'trainlm' type: help trainlm
% For a list of all training functions type: help nntrain
net.trainFcn = 'trainlm';  % Levenberg-Marquardt

% Choose a Performance Function
% For a list of all performance functions type: help nnperformance
net.performFcn = 'mse';  % Mean squared error

% Choose Plot Functions
% For a list of all plot functions type: help nnplot
net.plotFcns = {'plotperform','plottrainstate','ploterrhist', ...
  'plotregression', 'plotfit'};


% Train the Network
[net,tr] = train(net,inputs,targets);

% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)

% Recalculate Training, Validation and Test Performance
trainTargets = targets .* tr.trainMask{1};
valTargets = targets  .* tr.valMask{1};
testTargets = targets  .* tr.testMask{1};
trainPerformance = perform(net,trainTargets,outputs)
valPerformance = perform(net,valTargets,outputs)
testPerformance = perform(net,testTargets,outputs)

% View the Network
view(net)

% Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
%figure, plottrainstate(tr)
%figure, plotconfusion(targets,outputs)
%figure, ploterrhist(errors)