<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="it">
		<id>http://qualiwiki.homepc.it/index.php?action=history&amp;feed=atom&amp;title=Deep_Learning_Halcon</id>
		<title>Deep Learning Halcon - Cronologia</title>
		<link rel="self" type="application/atom+xml" href="http://qualiwiki.homepc.it/index.php?action=history&amp;feed=atom&amp;title=Deep_Learning_Halcon"/>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;action=history"/>
		<updated>2026-04-08T17:15:10Z</updated>
		<subtitle>Cronologia della pagina su questo sito</subtitle>
		<generator>MediaWiki 1.29.3</generator>

	<entry>
		<id>http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=593&amp;oldid=prev</id>
		<title>Qualivision il 15:30, 1 apr 2025</title>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=593&amp;oldid=prev"/>
				<updated>2025-04-01T15:30:41Z</updated>
		
		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;tr style='vertical-align: top;' lang='it'&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;← Versione meno recente&lt;/td&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;Versione delle 15:30, 1 apr 2025&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l6&quot; &gt;Riga 6:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Riga 6:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Creando una rete che usa come device una scheda video con TensorRT il processo di apply model (caricamento rete in vram) potrebbe essere lento.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Creando una rete che usa come device una scheda video con TensorRT il processo di apply model (caricamento rete in vram) potrebbe essere lento.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt;&amp;#160;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il problema è risolvibile in 2 modi:&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il problema è risolvibile in 2 modi:&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l18&quot; &gt;Riga 18:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Riga 19:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt;&amp;#160;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Se si usa un modello ottimizzato per TensorRT bisogna usare un device che abbia a sua volta TensorRT se non da errore.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Se si usa un modello ottimizzato per TensorRT bisogna usare un device che abbia a sua volta TensorRT se non da errore.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Qualivision</name></author>	</entry>

	<entry>
		<id>http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=592&amp;oldid=prev</id>
		<title>Qualivision: /* Ottimizzazione Modello */</title>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=592&amp;oldid=prev"/>
				<updated>2025-04-01T15:26:56Z</updated>
		
		<summary type="html">&lt;p&gt;‎&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;Ottimizzazione Modello&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;tr style='vertical-align: top;' lang='it'&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;← Versione meno recente&lt;/td&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;Versione delle 15:26, 1 apr 2025&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l18&quot; &gt;Riga 18:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Riga 18:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt;&amp;#160;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Se si usa un modello ottimizzato per TensorRT bisogna usare un device che abbia a sua volta TensorRT se non da errore.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Qualivision</name></author>	</entry>

	<entry>
		<id>http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=590&amp;oldid=prev</id>
		<title>Qualivision: Qualivision ha spostato la pagina Deep Learning a Deep Learning Halcon</title>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=590&amp;oldid=prev"/>
				<updated>2025-04-01T15:19:07Z</updated>
		
		<summary type="html">&lt;p&gt;Qualivision ha spostato la pagina &lt;a href=&quot;/index.php/Deep_Learning&quot; class=&quot;mw-redirect&quot; title=&quot;Deep Learning&quot;&gt;Deep Learning&lt;/a&gt; a &lt;a href=&quot;/index.php/Deep_Learning_Halcon&quot; title=&quot;Deep Learning Halcon&quot;&gt;Deep Learning Halcon&lt;/a&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;tr style='vertical-align: top;' lang='it'&gt;
				&lt;td colspan='1' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;← Versione meno recente&lt;/td&gt;
				&lt;td colspan='1' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;Versione delle 15:19, 1 apr 2025&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan='2' style='text-align: center;' lang='it'&gt;&lt;div class=&quot;mw-diff-empty&quot;&gt;(Nessuna differenza)&lt;/div&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;</summary>
		<author><name>Qualivision</name></author>	</entry>

	<entry>
		<id>http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=589&amp;oldid=prev</id>
		<title>Qualivision: /* Ottimizzazione Modello */</title>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=589&amp;oldid=prev"/>
				<updated>2025-04-01T15:18:09Z</updated>
		
		<summary type="html">&lt;p&gt;‎&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;Ottimizzazione Modello&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;col class='diff-marker' /&gt;
				&lt;col class='diff-content' /&gt;
				&lt;tr style='vertical-align: top;' lang='it'&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;← Versione meno recente&lt;/td&gt;
				&lt;td colspan='2' style=&quot;background-color: white; color:black; text-align: center;&quot;&gt;Versione delle 15:18, 1 apr 2025&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l9&quot; &gt;Riga 9:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Riga 9:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;1) Ottimizzare il livello da Deep Learning Tool:&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;1) Ottimizzare il livello da Deep Learning Tool:&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del class=&quot;diffchange diffchange-inline&quot;&gt;&amp;#160;  &lt;/del&gt;Sulla pagina &amp;quot;Evaluation&amp;quot; nella sezione &amp;quot;Inference and evaluation settings&amp;quot; impostare come device la GPU con TensorRt;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt; - &lt;/ins&gt;Sulla pagina &amp;quot;Evaluation&amp;quot; nella sezione &amp;quot;Inference and evaluation settings&amp;quot; impostare come device la GPU con TensorRt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del class=&quot;diffchange diffchange-inline&quot;&gt;&amp;#160;  &lt;/del&gt;Rieseguire l'evaluation ed esportare il modello dalla pagina &amp;quot;Export&amp;quot;.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt; - &lt;/ins&gt;Rieseguire l'evaluation ed esportare il modello dalla pagina &amp;quot;Export&amp;quot;.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;2) Ottimizzare il modello tramite Halcon:&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;2) Ottimizzare il modello tramite Halcon:&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del class=&quot;diffchange diffchange-inline&quot;&gt;&amp;#160;  &lt;/del&gt;Aprire il seguente script: \\QVSERVER\__Projects\DEEP LEARNING\HalconDL\optimize_model.hdev;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt; - &lt;/ins&gt;Aprire il seguente script: \\QVSERVER\__Projects\DEEP LEARNING\HalconDL\optimize_model.hdev;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del class=&quot;diffchange diffchange-inline&quot;&gt;&amp;#160;  &lt;/del&gt;Inserire in read_dl_model il file del modello '''NON OTTIMIZZATO''' e lanciare lo script;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt; - &lt;/ins&gt;Inserire in read_dl_model il file del modello '''NON OTTIMIZZATO''' e lanciare lo script;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del class=&quot;diffchange diffchange-inline&quot;&gt;&amp;#160;  &lt;/del&gt;Salvare il DLModelHandleConverted.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt; - &lt;/ins&gt;Salvare il DLModelHandleConverted.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;&amp;#160;&lt;/td&gt;&lt;td style=&quot;background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Qualivision</name></author>	</entry>

	<entry>
		<id>http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=588&amp;oldid=prev</id>
		<title>Qualivision: Creata pagina con &quot; Deep Learning livello PRO  == Ottimizzazione Modello == ----  Creando una rete che usa come device una scheda video con TensorRT il processo di apply model (caricamento rete...&quot;</title>
		<link rel="alternate" type="text/html" href="http://qualiwiki.homepc.it/index.php?title=Deep_Learning_Halcon&amp;diff=588&amp;oldid=prev"/>
				<updated>2025-04-01T15:17:26Z</updated>
		
		<summary type="html">&lt;p&gt;Creata pagina con &amp;quot; Deep Learning livello PRO  == Ottimizzazione Modello == ----  Creando una rete che usa come device una scheda video con TensorRT il processo di apply model (caricamento rete...&amp;quot;&lt;/p&gt;
&lt;p&gt;&lt;b&gt;Nuova pagina&lt;/b&gt;&lt;/p&gt;&lt;div&gt;&lt;br /&gt;
Deep Learning livello PRO&lt;br /&gt;
&lt;br /&gt;
== Ottimizzazione Modello ==&lt;br /&gt;
----&lt;br /&gt;
&lt;br /&gt;
Creando una rete che usa come device una scheda video con TensorRT il processo di apply model (caricamento rete in vram) potrebbe essere lento.&lt;br /&gt;
Il problema è risolvibile in 2 modi:&lt;br /&gt;
&lt;br /&gt;
1) Ottimizzare il livello da Deep Learning Tool:&lt;br /&gt;
   Sulla pagina &amp;quot;Evaluation&amp;quot; nella sezione &amp;quot;Inference and evaluation settings&amp;quot; impostare come device la GPU con TensorRt;&lt;br /&gt;
   Rieseguire l'evaluation ed esportare il modello dalla pagina &amp;quot;Export&amp;quot;.&lt;br /&gt;
&lt;br /&gt;
2) Ottimizzare il modello tramite Halcon:&lt;br /&gt;
   Aprire il seguente script: \\QVSERVER\__Projects\DEEP LEARNING\HalconDL\optimize_model.hdev;&lt;br /&gt;
   Inserire in read_dl_model il file del modello '''NON OTTIMIZZATO''' e lanciare lo script;&lt;br /&gt;
   Salvare il DLModelHandleConverted.&lt;br /&gt;
&lt;br /&gt;
Il modello viene ottimizzato per il device che viene utilizzato in quel momento, per esempio un modello ottimizzato su pc di laboratorio non sarà ottimizzato per il pc del cliente.&lt;/div&gt;</summary>
		<author><name>Qualivision</name></author>	</entry>

	</feed>