I have xml file as a trained output of my neural network program. Anyone can explain this one by one? How can I get trained weights using CvANN_MLP? Is openCV set init weights in zero?

asked 2015-05-03 06:36:42 -0500

 <?xml version="1.0"?>

<opencv_storage>

<ANN type_id="opencv-ml-ann-mlp">

  <layer_sizes type_id="opencv-matrix">

    <rows>1</rows>

    <cols>3</cols>

    <dt>i</dt>

    <data>

      300 2 1</data></layer_sizes>

  <activation_function>SIGMOID_SYM</activation_function>

  <f_param1>1.</f_param1>

  <f_param2>1.</f_param2>

  <min_val>-9.4999999999999996e-001</min_val>

  <max_val>9.4999999999999996e-001</max_val>

  <min_val1>-9.7999999999999998e-001</min_val1>

  <max_val1>9.7999999999999998e-001</max_val1>

  <training_params>

    <train_method>BACKPROP</train_method>

    <dw_scale>1.0000000000000001e-001</dw_scale>

    <moment_scale>1.0000000000000001e-001</moment_scale>

    <term_criteria><epsilon>9.9999997473787516e-005</epsilon>

      <iterations>2</iterations></term_criteria></training_params>

  <input_scale>

    1.9107005094445375e+002 -5.3748005017866243e+000

    1.9107004409716646e+002 -5.3939073167140332e+000

    1.9107005513684737e+002 -5.4130146370097902e+000

    1.9107005394582654e+002 -5.4321216355210158e+000

    1.9107006375984025e+002 -5.4512289121781006e+000

    1.9107006310153125e+002 -5.4703359384281534e+000

    1.9107004797772859e+002 -5.4894425489529057e+000

    1.9107005001329222e+002 -5.5085495799782906e+000

    1.9107003824167413e+002 -5.5276562594217769e+000

    1.9107004380265940e+002 -5.5467633684972828e+000

    1.9107004207892663e+002 -5.5658703376602841e+000

    1.9107004965815111e+002 -5.5849775309512211e+000

    1.9107004409716646e+002 -5.6040843640820501e+000

    1.9107005513684737e+002 -5.6231916965214559e+000

    1.9107005394582654e+002 -5.6422986937225588e+000

    1.9107006375984025e+002 -5.6614059811750588e+000

    1.9107006382480591e+002 -5.6805130163407371e+000

    1.9107004797772859e+002 -5.6996196005895410e+000

    1.9107005073656637e+002 -5.7187266436384512e+000

    1.9107003824167452e+002 -5.7378333003487647e+000

    1.9107004307938416e+002 -5.7569404056122480e+000

    1.9107004207892700e+002 -5.7760473828082484e+000

    1.9107004893487584e+002 -5.7951545743625719e+000

    1.9107004409716646e+002 -5.8142614114500670e+000

    1.9107005441357282e+002 -5.8333687458147407e+000

    1.9107005427931247e+002 -5.8524757502755849e+000

    1.9107006375984025e+002 -5.8715830501720170e+000

    1.9107006415829113e+002 -5.8906900838273151e+000

    1.9107004818128470e+002 -5.9097966466589771e+000

    1.9107005040308047e+002 -5.9289036998249305e+000

    1.9107003844523018e+002 -5.9480103357492391e+000

    1.9107004274589832e+002 -5.9671174533091316e+000

    1.9107004187537055e+002 -5.9862244334419685e+000

    1.9107004860138994e+002 -6.0053316284337974e+000

    1.9107004389361003e+002 -6.0244384642631390e+000

    1.9107005441357242e+002 -6.0435458045307913e+000

    1.9107005407575676e+002 -6.0626528142483309e+000

    1.9107006375984062e+002 -6.0817601191689876e+000

    1.9107006415829264e+002 -6.1008671532626177e+000

    1.9107004818128394e+002 -6.1199736985194981e+000

    1.9107005008691740e+002 -6.1390807321079430e+000

    1.9107003844523095e+002 -6.1581873769001509e+000

    1.9107004242973679e+002 -6.1772944771060621e+000

    1.9107004187537129e+002 -6.1964014783660337e+000

    1.9107004891755224e+002 -6.2155087029044100e+000

    1.9107004336089784e+002 -6.2346154821616553e+000

    1.9107005472973552e+002 -6.2537228854580631e+000

    1.9107005292371284e+002 -6.2728298110448133e+000

    1.9107006341336236e+002 -6.2919371767564165e+000

    1.9107006407167100e+002 -6.3110442198367602e+000

    1.9107004751864420e+002 -6.3301507165636011e+000

    1.9107005123896050e+002 -6.3492578480734592e+000

    1.9107003910787211e+002 -6.3683644520000575e+000

    1.9107004358177821e+002 -6.3874715848790302e+000

    1.9107004253801099e+002 -6.4065785573715743e+000

    1.9107004857107256e+002 -6.4256857439227399e+000

    1.9107004402354056e+002 -6.4447925629339053e+000

    1.9107005376392416e+002 -6.4638998999853170e+000

    1.9107005182797474e+002 -6.4830068190804484e+000

    1.9107006437917087e+002 -6.5021142901019022e+000

    1.9107006061121211e+002 -6.5212211354816976e+000

    1.9107004725878386e+002 -6.5403277588002240e+000

    1.9107004870100008e+002 -6.5594347924428869e+000

    1.9107003884801182e+002 -6.5785414849328605e+000

    1.9107004577325571e+002 -6.5976487310782179e+000

    1.9107004376367948e+002 -6.6167556573326101e+000

    1.9107005330050845e+002 -6.6358630079181227e+000

    1.9107004376367948e+002 -6.6549696011699728e+000

    1.9107005739762144e+002 -6.6740771205013854e+000

    1.9107005156811437e+002 -6.6931838658494458e+000

    1.9107006403269258e+002 -6.7122913476083417e+000 ...
(more)
edit retag flag offensive close merge delete