|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>Training and Testing</TITLE
><link href="../style.css" rel="stylesheet" type="text/css"><META
NAME="GENERATOR"
CONTENT="Modular DocBook HTML Stylesheet Version 1.7"><LINK
REL="HOME"
TITLE="Fast Artificial Neural Network Library"
HREF="index.html"><LINK
REL="UP"
TITLE="Advanced Usage"
HREF="c104.html"><LINK
REL="PREVIOUS"
TITLE="Understanding the Error Value"
HREF="x148.html"><LINK
REL="NEXT"
TITLE="Avoid Over-Fitting"
HREF="x181.html"></HEAD
><BODY
CLASS="section"
BGCOLOR="#FFFFFF"
TEXT="#000000"
LINK="#0000FF"
VLINK="#840084"
ALINK="#0000FF"
><DIV
CLASS="NAVHEADER"
><TABLE
SUMMARY="Header navigation table"
WIDTH="100%"
BORDER="0"
CELLPADDING="0"
CELLSPACING="0"
><TR
><TH
COLSPAN="3"
ALIGN="center"
>Fast Artificial Neural Network Library</TH
></TR
><TR
><TD
WIDTH="10%"
ALIGN="left"
VALIGN="bottom"
><A
HREF="x148.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
>Chapter 2. Advanced Usage</TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="x181.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><DIV
CLASS="section"
><H1
CLASS="section"
><A
NAME="adv.train_test"
>2.4. Training and Testing</A
></H1
><P
> Normally it will be sufficient to use the <A
HREF="r806.html"
><CODE
CLASS="function"
>fann_train_on_file</CODE
></A
> training function, but
sometimes you want to have more control and you will have to write a custom training loop. This could be because you would like another stop criteria,
or because you would like to adjust some of the parameters during training. Another stop criteria than the value of the combined mean square error could
be that each of the training pairs should have a mean square error lower than a given value.
</P
><DIV
CLASS="example"
><A
NAME="example.train_on_file_internals"
></A
><P
><B
>Example 2-1.
The internals of the <CODE
CLASS="function"
>fann_train_on_file</CODE
> function, without writing the status line.
</B
></P
><PRE
CLASS="programlisting"
>
struct fann_train_data *data = fann_read_train_from_file(filename);
for(i = 1 ; i <= max_epochs ; i++) {
fann_reset_MSE(ann);
for (j = 0 ; j != data->num_data ; j++) {
fann_train(ann, data->input[j], data->output[j]);
}
if ( fann_get_MSE(ann) < desired_error ) {
break;
}
}
fann_destroy_train(data);
</PRE
></DIV
><P
> This piece of code introduces the <A
HREF="r536.html"
><CODE
CLASS="function"
>fann_train</CODE
></A
> function, which trains the ANN for one iteration
with one pair of inputs and outputs and also updates the mean square error. The
<A
HREF="r1837.html"
><SPAN
CLASS="type"
>fann_train_data</SPAN
></A
> structure is also introduced, this structure is a container for the
training data in the file described in figure 10. The structure can be used to train the ANN, but it can also be used to test the ANN with data which it
has not been trained with.
</P
><DIV
CLASS="example"
><A
NAME="example.calc_mse"
></A
><P
><B
>Example 2-2. Test all of the data in a file and calculates the mean square error.</B
></P
><PRE
CLASS="programlisting"
>
struct fann_train_data *data = fann_read_train_from_file(filename);
fann_reset_MSE(ann);
for(i = 0 ; i != data->num_data ; i++ ) {
fann_test(ann, data->input[i], data->output[i]);
}
printf("Mean Square Error: %f\n", fann_get_MSE(ann));
fann_destroy_train(data);
</PRE
></DIV
><P
> This piece of code introduces another useful function: <A
HREF="r557.html"
><CODE
CLASS="function"
>fann_test</CODE
></A
> function, which takes an input
array and a desired output array as the parameters and returns the calculated output. It also updates the mean square error.
</P
></DIV
><DIV
CLASS="NAVFOOTER"
><HR
ALIGN="LEFT"
WIDTH="100%"><TABLE
SUMMARY="Footer navigation table"
WIDTH="100%"
BORDER="0"
CELLPADDING="0"
CELLSPACING="0"
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
><A
HREF="x148.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="index.html"
ACCESSKEY="H"
>Home</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
><A
HREF="x181.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Understanding the Error Value</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="c104.html"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Avoid Over-Fitting</TD
></TR
></TABLE
></DIV
></BODY
></HTML
>
|
By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.
If a file you wish to view isn't highlighted, and is a text file (not binary), please
let us know and we'll add colourisation support for it.