|
»
»
»
»
Request for a Clarification on Every Run Output Differences
|
View:
New views
8 Messages
—
Rating Filter:
Alert me
|
 |
Request for a Clarification on Every Run Output Differences
by Othman Soufan
::
Rate this Message:
Dear Group,
After I have installed FANN, I went and tried to run the example on the "Getting Started" page. However, each time I run the program on the Xor.data, I get a different output. I would like to mention that I have combined the training and testing programs in one program. Some output samples are: Max epochs 500000. Desired error: 0.0010000000. Epochs 1. Current error: 0.2505536079. Bit fail 4. Epochs 26. Current error: 0.0007957527. Bit fail 0. xor test (-1.000000,1.000000) -> -319531589830587711488.000000 Max epochs 500000. Desired error: 0.0010000000. Epochs 1. Current error: 0.2500049174. Bit fail 4. Epochs 23. Current error: 0.0009584196. Bit fail 0. xor test (-1.000000,1.000000) -> -0.000002 Max epochs 500000. Desired error: 0.0010000000. Epochs 1. Current error: 0.2502186596. Bit fail 4. Epochs 30. Current error: 0.0009348781. Bit fail 0. xor test (-1.000000,1.000000) -> 0.000000 I would like to know why I am receiving such weird outputs that differs from each other. Regards, Othman ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Steffen Nissen
::
Rate this Message:
Weight are initialized randomly, so different result is expected. The very large number you observed in the first run is, however, not expected.
On Monday, March 19, 2012, Othman Soufan <othman.soufan@...> wrote: > Dear Group, > > After I have installed FANN, I went and tried to run the example on the "Getting Started" page. > However, each time I run the program on the Xor.data, I get a different output. > I would like to mention that I have combined the training and testing programs in one program. > > Some output samples are: > Max epochs 500000. Desired error: 0.0010000000. > Epochs 1. Current error: 0.2505536079. Bit fail 4. > Epochs 26. Current error: 0.0007957527. Bit fail 0. > xor test (-1.000000,1.000000) -> -319531589830587711488.000000 > > Max epochs 500000. Desired error: 0.0010000000. > Epochs 1. Current error: 0.2500049174. Bit fail 4. > Epochs 23. Current error: 0.0009584196. Bit fail 0. > xor test (-1.000000,1.000000) -> -0.000002 > > Max epochs 500000. Desired error: 0.0010000000. > Epochs 1. Current error: 0.2502186596. Bit fail 4. > Epochs 30. Current error: 0.0009348781. Bit fail 0. > xor test (-1.000000,1.000000) -> 0.000000 > > I would like to know why I am receiving such weird outputs that differs > from each other. > > Regards, > Othman > -- Best Regards, Steffen Nissen, MSc http://www.linkedin.com/in/steffennissen ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Fábio Blessa
::
Rate this Message:
Send us the code plz...
For sure has a small mistake. BR, Fábio
On Sun, Mar 18, 2012 at 10:06 PM, Steffen Nissen <sn@...> wrote: Weight are initialized randomly, so different result is expected. The very large number you observed in the first run is, however, not expected. ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Othman Soufan
::
Rate this Message:
Thanks for the immediate response.
The code is as follows: #include <stdio.h> #include <stdlib.h> #include <fann.h> #include "floatfann.h" #include "libMSVM.h" // Generic structure and function declarations #include "libtrainMSVM.h" // Training functions (not required for predictions only) #include "libevalMSVM.h" // Evaluation functions (also used during training) #include "memory.c" #include "math.h" //1. Consider having a matrix for the output layer when we have multiple class i.e. one-to-all representation int main() { const unsigned int num_input = 2; const unsigned int num_output = 1; const unsigned int num_layers = 3; const unsigned int num_neurons_hidden = 3; const float desired_error = (const float) 0.001; const unsigned int max_epochs = 500000; const unsigned int epochs_between_reports = 1000; //Training the ANN struct fann *ann = fann_create_standard(num_layers, num_input, num_neurons_hidden, num_output); fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC); fann_set_activation_function_output(ann, FANN_SIGMOID_SYMMETRIC); fann_train_on_file(ann, "xor.data", max_epochs, epochs_between_reports, desired_error); //Testing the ANN fann_type *calc_out; fann_type input[2]; input[0] = -1; input[1] = 1; calc_out = fann_run(ann, input); printf("xor test (%f,%f) -> %f\n", input[0], input[1], calc_out[0]); fann_destroy(ann); return 0; } 2012/3/19 Fábio Blessa <fabioblessa@...> Send us the code plz... -- MS Candidate, Class of 2010 Mathematical and Computer Sciences and Engineering King Abdullah University of Science and Technology Tuwal, Jeddah, KSA. Mobile: +966506134003 ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Othman Soufan
::
Rate this Message:
I would like to update you that:
const unsigned int num_output = 2; solves the problem. So, instead of setting num_output = 1 as listed on the Getting Started page, num_output = 2 seems to overcome the problem of large output differences. Currently, whenever I execute the program I get the following output: xor test (-1.000000,1.000000) -> 0.000000 So, would you kindly confirm if this is the proper solution or am I missing something? Regards, Othman On Mon, Mar 19, 2012 at 4:58 AM, Othman Soufan <othman.soufan@...> wrote:
------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Steffen Nissen
::
Rate this Message:
That should not fix anything, as the XOR problem only has one output.
Please let me know how you compile the source, perhaps you are linking with doublefann instead of floatfann. You can also try to run some of the other examples in: http://fann.git.sourceforge.net/git/gitweb.cgi?p=fann/fann;a=tree;f=examples;hb=HEAD Like: http://fann.git.sourceforge.net/git/gitweb.cgi?p=fann/fann;a=blob;f=examples/cascade_train.c;h=35bae4b9a0e022770c97995d6301aab6e08680e8;hb=HEAD Steffen On Monday, 19 March 2012, Othman Soufan <othman.soufan@...> wrote: > I would like to update you that: > > const unsigned int num_output = 2; > > solves the problem. > > So, instead of setting num_output = 1 as listed on the Getting Started page, > num_output = 2 seems to overcome the problem of large output differences. > > Currently, whenever I execute the program I get the following output: > xor test (-1.000000,1.000000) -> 0.000000 > > So, would you kindly confirm if this is the proper solution or am I missing > something? > > Regards, > Othman > > On Mon, Mar 19, 2012 at 4:58 AM, Othman Soufan <othman.soufan@...> wrote: > > Thanks for the immediate response. > > The code is as follows: > > #include <stdio.h> > #include <stdlib.h> > #include <fann.h> > #include "floatfann.h" > #include "libMSVM.h" // Generic structure and function declarations > #include "libtrainMSVM.h" // Training functions (not required for predictions only) > #include "libevalMSVM.h" // Evaluation functions (also used during training) > #include "memory.c" > #include "math.h" > > //1. Consider having a matrix for the output layer when we have multiple class i.e. one-to-all representation > > int main() > { > const unsigned int num_input = 2; > const unsigned int num_output = 1; > const unsigned int num_layers = 3; > const unsigned int num_neurons_hidden = 3; > const float desired_error = (const float) 0.001; > const unsigned int max_epochs = 500000; > const unsigned int epochs_between_reports = 1000; > > //Training the ANN > struct fann *ann = fann_create_standard(num_layers, num_input, num_neurons_hidden, num_output); > > fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC); > fann_set_activation_function_output(ann, FANN_SIGMOID_SYMMETRIC); > > fann_train_on_file(ann, "xor.data", max_epochs, epochs_between_reports, desired_error); > > //Testing the ANN > fann_type *calc_out; > fann_type input[2]; > > input[0] = -1; > input[1] = 1; > calc_out = fann_run(ann, input); > printf("xor test (%f,%f) -> %f\n", input[0], input[1], calc_out[0]); > > fann_destroy(ann); > > return 0; > } > > > 2012/3/19 Fábio Blessa <fabioblessa@...> > > Send us the code plz... > For sure has a small mistake. > BR, > Fábio > > On Sun, Mar 18, 2012 at 10:06 PM, Steffen Nissen <sn@...> wrote: > > Weight are initialized randomly, so different result is expected. The very large number you observed in the first run is, however, not expected. > > On Monday, March 19, 2012, Othman Soufan <othman.soufan@...> wrote: >> Dear Group, >> >> After I have installed FANN, I went and tried to run the example on the "Getting Started" page. >> However, each time I run the program on the Xor.data, I get a different output. >> I would like to mention that I have combined the training and testing programs in one program. >> >> Some output samples are: >> Max epochs 500000. Desired error: 0.0010000000. >> Epochs 1. Current error: 0.2505536079. Bit fail 4. >> Epochs 26. Current error: 0.0007957527. Bit fail 0. >> xor test (-1.000000,1.000000) -> -319531589830587711488.000000 >> >> Max epochs 500000. Desired error: 0.0010000000. >> Epochs 1. Current error: 0.2500049174. Bit fail 4. >> Epochs 23. Current error: 0.0009584196. Bit fail 0. >> xor test (-1.000000,1.000000) -> -0.000002 >> >> Max epochs 500000. Desired error: 0.0010000000. >> Epochs 1. Current error: 0.2502186596. Bit fail 4. >> Epochs 30. Current error: 0.0009348781. Bit fail 0. >> xor test (-1.000000,1.000000) -> 0.000000 >> >> I would like to know why I am receiving such weird outputs that differs >> from each other. >> >> Regards, >> Othman >> > > -- > Best Regards, > Steffen Nissen, MSc > http://www.linkedin.com/in/steffennissen > > ------------------------------------------------------------------------------ > This SF email is sponsosred by: > Try Windows Azure free for 90 days Click Here > ht -- Best Regards, Steffen Nissen, MSc http://www.linkedin.com/in/steffennissen ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Othman Soufan
::
Rate this Message:
Indeed that was the problem...
I was linking to doublefann instead of floatfann. Now, I am getting the right output which is: xor test (-1.000000,1.000000) -> 1.000000 As the printf in the example is using "%f ", the floatfann should be linked only. Thanks for the support and I appreciate your efforts. On Mon, Mar 19, 2012 at 4:12 PM, Steffen Nissen <sn@...> wrote: That should not fix anything, as the XOR problem only has one output. -- MS Candidate, Class of 2010 Mathematical and Computer Sciences and Engineering King Abdullah University of Science and Technology Tuwal, Jeddah, KSA. Mobile: +966506134003 ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
|
|
Re: Request for a Clarification on Every Run Output Differences
by Steffen Nissen
::
Rate this Message:
Please note that whenever you include floatfann.h or just fann.h instead of doublefann.h, you should link with floatfann.
On Monday, 19 March 2012, Othman Soufan <othman.soufan@...> wrote: > Indeed that was the problem... > I was linking to doublefann instead of floatfann. > > Now, I am getting the right output which is: > xor test (-1.000000,1.000000) -> 1.000000 > > As the printf in the example is using "%f ", the floatfann > should be linked only. > > Thanks for the support and I appreciate your efforts. > > On Mon, Mar 19, 2012 at 4:12 PM, Steffen Nissen <sn@...> wrote: >> >> That should not fix anything, as the XOR problem only has one output. >> >> Please let me know how you compile the source, perhaps you are linking with doublefann instead of floatfann. >> >> You can also try to run some of the other examples in: >> http://fann.git.sourceforge.net/git/gitweb.cgi?p=fann/fann;a=tree;f=examples;hb=HEAD >> >> Like: >> http://fann.git.sourceforge.net/git/gitweb.cgi?p=fann/fann;a=blob;f=examples/cascade_train.c;h=35bae4b9a0e022770c97995d6301aab6e08680e8;hb=HEAD >> >> Steffen >> >> On Monday, 19 March 2012, Othman Soufan <othman.soufan@...> wrote: >> > I would like to update you that: >> > >> > const unsigned int num_output = 2; >> > >> > solves the problem. >> > >> > So, instead of setting num_output = 1 as listed on the Getting Started page, >> > num_output = 2 seems to overcome the problem of large output differences. >> > >> > Currently, whenever I execute the program I get the following output: >> > xor test (-1.000000,1.000000) -> 0.000000 >> > >> > So, would you kindly confirm if this is the proper solution or am I missing >> > something? >> > >> > Regards, >> > Othman >> > >> > On Mon, Mar 19, 2012 at 4:58 AM, Othman Soufan <othman.soufan@...> wrote: >> > >> > Thanks for the immediate response. >> > >> > The code is as follows: >> > >> > #include <stdio.h> >> > #include <stdlib.h> >> > #include <fann.h> >> > #include "floatfann.h" >> > #include "libMSVM.h" // Generic structure and function declarations >> > #include "libtrainMSVM.h" // Training functions (not required for predictions only) >> > #include "libevalMSVM.h" // Evaluation functions (also used during training) >> > #include "memory.c" >> > #include "math.h" >> > >> > //1. Consider having a matrix for the output layer when we have multiple class i.e. one-to-all representation >> > >> > int main() >> > { >> > const unsigned int num_input = 2; >> > const unsigned int num_output = 1; >> > const unsigned int num_layers = 3; >> > const unsigned int num_neurons_hidden = 3; >> > const float desired_error = (const float) 0.001; >> > const unsigned int max_epochs = 500000; >> > const unsigned int epochs_between_reports = 1000; >> > >> > //Training the ANN >> > struct fann *ann = fann_create_standard(num_layers, num_input, num_neurons_hidden, num_output); >> > >> > fann_set_activation_function_hidden(ann, FANN_SIGMOID_SYMMETRIC); >> > fann_set_activation_function_output(ann, FANN_SIGMOID_SYMMETRIC); >> > >> > fann_train_on_file(ann, "xor.data", max_epochs, epochs_between_reports, desired_error); >> > >> > //Testing the ANN >> > fann_type *calc_out; >> > fann_type input[2]; >> > >> > input[0] = -1; >> > input[1] = 1; >> > calc_out = fann_run(ann, input); >> > printf("xor test (%f,%f) -> %f\n", input[0], input[1], calc_out[0]); >> > >> > fann_destroy(ann); >> > >> > return 0; >> > } >> > >> > >> > 2012/3/19 Fábio Blessa <fabioblessa@...> >> > >> > Send us the code plz... >> > For sure has a small mistake. >> > BR, >> > Fábio >> > >> > On Sun, Mar 18, 2012 at 10:06 PM, Steffen Nissen <sn@...> wrote: >> > >> > Weight are initialized randomly, so different result is expected. The very large number you observed in the first run is, however, not expected. >> > >> > On Monday, March 19, 2012, Othman Soufan <othman.soufan@...> wrote: >> >> Dear Group, >> >> >> >> After I have installed FANN, I went and tried to run the example on the "Getting Started" page. >> >> However, each time I run the program on the Xor.data, I get a different output. >> >> I would like to mention that I have combined the training and testing programs in one program. >> >> >> >> Some output samples are: >> >> Max epochs 5 >> http://p.sf.net/sfu/sfd2d-msazure >> _______________________________________________ >> Fann-general mailing list >> Fann-general@... >> https://lists.sourceforge.net/lists/listinfo/fann-general >> > > > > -- > MS Candidate, Class of 2010 > Mathematical and Computer Sciences and Engineering > King Abdullah University of Science and Technology > Tuwal, Jeddah, KSA. > Mobile: +966506134003 > > -- Best Regards, Steffen Nissen, MSc http://www.linkedin.com/in/steffennissen ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Fann-general mailing list Fann-general@... https://lists.sourceforge.net/lists/listinfo/fann-general |
| Free embeddable forum powered by Nabble | Forum Help |
