<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: How to export and use a trained outmodel in Proc NNET for later use in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/941911#M10907</link>
    <description>&lt;P&gt;Tell us about the SAS version you are using.&lt;BR /&gt;Submit&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;%PUT &amp;amp;=sysvlong4;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;... and tell us what's in the log-screen.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;If I look at the latest 2024.08 documentation&lt;BR /&gt;(&lt;A href="https://go.documentation.sas.com/doc/en/pgmsascdc/v_054/casml/casml_nnet_syntax12.htm" target="_blank"&gt;https://go.documentation.sas.com/doc/en/pgmsascdc/v_054/casml/casml_nnet_syntax12.htm&lt;/A&gt;&lt;SPAN&gt;) , there is a&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;
&lt;UL class="lia-list-style-type-square"&gt;
&lt;LI&gt;SAVESTATE Statement (to create &lt;SPAN&gt;an analytic store)&amp;nbsp;&lt;/SPAN&gt;and a&amp;nbsp;&lt;/LI&gt;
&lt;LI&gt;CODE Statement (that&amp;nbsp;&lt;SPAN&gt;returns the SAS score code)&lt;/SPAN&gt;&lt;/LI&gt;
&lt;/UL&gt;
&lt;P&gt;Both ways can be &lt;SPAN&gt;used to score data similar to the input data.&lt;BR /&gt;&lt;BR /&gt;Koen&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Fri, 30 Aug 2024 07:12:59 GMT</pubDate>
    <dc:creator>sbxkoenk</dc:creator>
    <dc:date>2024-08-30T07:12:59Z</dc:date>
    <item>
      <title>How to export and use a trained outmodel in Proc NNET for later use</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/941886#M10906</link>
      <description>&lt;P&gt;I have used to following code to train a neural net model:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="William29_0-1724985291295.png" style="width: 400px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/99784i499D39D1A1151012/image-size/medium?v=v2&amp;amp;px=400" role="button" title="William29_0-1724985291295.png" alt="William29_0-1724985291295.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;I then exported the model so that I can use it in a different sas file to score data using the following code which is part of the same file as the code above:&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="William29_1-1724985390247.png" style="width: 400px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/99785i479DED7C6CC750B2/image-size/medium?v=v2&amp;amp;px=400" role="button" title="William29_1-1724985390247.png" alt="William29_1-1724985390247.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;In a different file, I then import the model and use it to score new data using the following code:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="William29_2-1724985484612.png" style="width: 400px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/99786i4EFA5929EE97E46B/image-size/medium?v=v2&amp;amp;px=400" role="button" title="William29_2-1724985484612.png" alt="William29_2-1724985484612.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;However this generates the following error:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="William29_3-1724985593987.png" style="width: 400px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/99787iE2554384E6C2AC5D/image-size/medium?v=v2&amp;amp;px=400" role="button" title="William29_3-1724985593987.png" alt="William29_3-1724985593987.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;I have the feeling that you cant simple export and import a model generated by the inmodel statement like a normal dataset. So how do I export and import it. Different model types have a SAVESTATE statement that can be used with PROC ASTORE to properly IMPORT and EXPORT the model but PROC NNET does not have the option for a SAVESTATE statement so how can this be done?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 30 Aug 2024 02:42:03 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/941886#M10906</guid>
      <dc:creator>William29</dc:creator>
      <dc:date>2024-08-30T02:42:03Z</dc:date>
    </item>
    <item>
      <title>Re: How to export and use a trained outmodel in Proc NNET for later use</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/941911#M10907</link>
      <description>&lt;P&gt;Tell us about the SAS version you are using.&lt;BR /&gt;Submit&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;%PUT &amp;amp;=sysvlong4;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;... and tell us what's in the log-screen.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;If I look at the latest 2024.08 documentation&lt;BR /&gt;(&lt;A href="https://go.documentation.sas.com/doc/en/pgmsascdc/v_054/casml/casml_nnet_syntax12.htm" target="_blank"&gt;https://go.documentation.sas.com/doc/en/pgmsascdc/v_054/casml/casml_nnet_syntax12.htm&lt;/A&gt;&lt;SPAN&gt;) , there is a&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;
&lt;UL class="lia-list-style-type-square"&gt;
&lt;LI&gt;SAVESTATE Statement (to create &lt;SPAN&gt;an analytic store)&amp;nbsp;&lt;/SPAN&gt;and a&amp;nbsp;&lt;/LI&gt;
&lt;LI&gt;CODE Statement (that&amp;nbsp;&lt;SPAN&gt;returns the SAS score code)&lt;/SPAN&gt;&lt;/LI&gt;
&lt;/UL&gt;
&lt;P&gt;Both ways can be &lt;SPAN&gt;used to score data similar to the input data.&lt;BR /&gt;&lt;BR /&gt;Koen&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 30 Aug 2024 07:12:59 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/941911#M10907</guid>
      <dc:creator>sbxkoenk</dc:creator>
      <dc:date>2024-08-30T07:12:59Z</dc:date>
    </item>
    <item>
      <title>Re: How to export and use a trained outmodel in Proc NNET for later use</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/942121#M10912</link>
      <description>&lt;P&gt;When i put in that code i get the following:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;V.03.05M0P11112019&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Sun, 01 Sep 2024 23:20:40 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/How-to-export-and-use-a-trained-outmodel-in-Proc-NNET-for-later/m-p/942121#M10912</guid>
      <dc:creator>William29</dc:creator>
      <dc:date>2024-09-01T23:20:40Z</dc:date>
    </item>
  </channel>
</rss>

