{"id":27401,"date":"2024-03-16T08:25:14","date_gmt":"2024-03-16T08:25:14","guid":{"rendered":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/"},"modified":"2024-03-22T10:56:56","modified_gmt":"2024-03-22T10:56:56","slug":"how-do-we-use-nn-parameter-in-pytorch","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/","title":{"rendered":"How do we use nn.parameter in PyTorch?"},"content":{"rendered":"<p>In PyTorch, nn.Parameter is a special type of Tensor that represents trainable parameters in nn.Module. These nn.Parameter objects are automatically identified and registered as model&#8217;s trainable parameters by the nn.Module constructor.<\/p>\n<p>To use nn.Parameter in PyTorch, you first need to create an nn.Parameter object and assign it as an attribute of your model. Here is a simple example:<\/p>\n<pre class=\"post-pre\"><code><span class=\"hljs-keyword\">import<\/span> torch\r\n<span class=\"hljs-keyword\">import<\/span> torch.nn <span class=\"hljs-keyword\">as<\/span> nn\r\n\r\n<span class=\"hljs-keyword\">class<\/span> <span class=\"hljs-title class_\">MyModel<\/span>(nn.Module):\r\n    <span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title function_\">__init__<\/span>(<span class=\"hljs-params\">self<\/span>):\r\n        <span class=\"hljs-built_in\">super<\/span>(MyModel, self).__init__()\r\n        self.weight = nn.Parameter(torch.rand(<span class=\"hljs-number\">3<\/span>, <span class=\"hljs-number\">4<\/span>))  <span class=\"hljs-comment\"># \u521b\u5efa\u4e00\u4e2a\u53c2\u6570<\/span>\r\n\r\n    <span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title function_\">forward<\/span>(<span class=\"hljs-params\">self, x<\/span>):\r\n        out = torch.matmul(x, self.weight)\r\n        <span class=\"hljs-keyword\">return<\/span> out\r\n\r\nmodel = MyModel()\r\n<span class=\"hljs-built_in\">print<\/span>(model.weight)  <span class=\"hljs-comment\"># \u6253\u5370\u53c2\u6570<\/span>\r\n\r\n<\/code><\/pre>\n<p>In the example above, we defined a class called MyModel that inherits from nn.Module. In the constructor __init__, we created an nn.Parameter object self.weight, which is a randomly initialized Tensor with shape (3, 4).<\/p>\n<p>In the forward method, we can calculate using the self.weight parameter. Once the model is created, we can access this parameter through model.weight.<\/p>\n<p>It is important to note that nn.Parameter objects are automatically registered as trainable parameters of the model, and can be accessed in the model&#8217;s parameters() method. Additionally, nn.Parameter objects also automatically have the ability to compute gradients, which can be calculated automatically using the backward() method.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In PyTorch, nn.Parameter is a special type of Tensor that represents trainable parameters in nn.Module. These nn.Parameter objects are automatically identified and registered as model&#8217;s trainable parameters by the nn.Module constructor. To use nn.Parameter in PyTorch, you first need to create an nn.Parameter object and assign it as an attribute of your model. Here is [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-27401","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>How do we use nn.parameter in PyTorch? - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How do we use nn.parameter in PyTorch?\" \/>\n<meta property=\"og:description\" content=\"In PyTorch, nn.Parameter is a special type of Tensor that represents trainable parameters in nn.Module. These nn.Parameter objects are automatically identified and registered as model&#8217;s trainable parameters by the nn.Module constructor. To use nn.Parameter in PyTorch, you first need to create an nn.Parameter object and assign it as an attribute of your model. Here is [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/SiliCloudGlobal\/\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-16T08:25:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-22T10:56:56+00:00\" \/>\n<meta name=\"author\" content=\"Emily Johnson\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@SiliCloudGlobal\" \/>\n<meta name=\"twitter:site\" content=\"@SiliCloudGlobal\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Emily Johnson\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\"},\"author\":{\"name\":\"Emily Johnson\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/3b041b19cffc258705478ecfab895378\"},\"headline\":\"How do we use nn.parameter in PyTorch?\",\"datePublished\":\"2024-03-16T08:25:14+00:00\",\"dateModified\":\"2024-03-22T10:56:56+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\"},\"wordCount\":182,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/#organization\"},\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\",\"url\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\",\"name\":\"How do we use nn.parameter in PyTorch? - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/#website\"},\"datePublished\":\"2024-03-16T08:25:14+00:00\",\"dateModified\":\"2024-03-22T10:56:56+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.silicloud.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How do we use nn.parameter in PyTorch?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/blog\/\",\"name\":\"Silicon Cloud Blog\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/#organization\"},\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#organization\",\"name\":\"Silicon Cloud Blog\",\"url\":\"https:\/\/www.silicloud.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.silicloud.com\/blog\/wp-content\/uploads\/2023\/11\/EN-SILICON-Full.png\",\"contentUrl\":\"https:\/\/www.silicloud.com\/blog\/wp-content\/uploads\/2023\/11\/EN-SILICON-Full.png\",\"width\":1024,\"height\":1024,\"caption\":\"Silicon Cloud Blog\"},\"image\":{\"@id\":\"https:\/\/www.silicloud.com\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/SiliCloudGlobal\/\",\"https:\/\/twitter.com\/SiliCloudGlobal\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/3b041b19cffc258705478ecfab895378\",\"name\":\"Emily Johnson\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/a5cb4e73d02ab1d79f2dfe919389ff7c1de072baa97686392031c03d858cc358?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/a5cb4e73d02ab1d79f2dfe919389ff7c1de072baa97686392031c03d858cc358?s=96&d=mm&r=g\",\"caption\":\"Emily Johnson\"},\"url\":\"https:\/\/www.silicloud.com\/blog\/author\/emilyjohnson\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"How do we use nn.parameter in PyTorch? - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/","og_locale":"en_US","og_type":"article","og_title":"How do we use nn.parameter in PyTorch?","og_description":"In PyTorch, nn.Parameter is a special type of Tensor that represents trainable parameters in nn.Module. These nn.Parameter objects are automatically identified and registered as model&#8217;s trainable parameters by the nn.Module constructor. To use nn.Parameter in PyTorch, you first need to create an nn.Parameter object and assign it as an attribute of your model. Here is [&hellip;]","og_url":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/","og_site_name":"Blog - Silicon Cloud","article_publisher":"https:\/\/www.facebook.com\/SiliCloudGlobal\/","article_published_time":"2024-03-16T08:25:14+00:00","article_modified_time":"2024-03-22T10:56:56+00:00","author":"Emily Johnson","twitter_card":"summary_large_image","twitter_creator":"@SiliCloudGlobal","twitter_site":"@SiliCloudGlobal","twitter_misc":{"Written by":"Emily Johnson","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#article","isPartOf":{"@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/"},"author":{"name":"Emily Johnson","@id":"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/3b041b19cffc258705478ecfab895378"},"headline":"How do we use nn.parameter in PyTorch?","datePublished":"2024-03-16T08:25:14+00:00","dateModified":"2024-03-22T10:56:56+00:00","mainEntityOfPage":{"@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/"},"wordCount":182,"commentCount":0,"publisher":{"@id":"https:\/\/www.silicloud.com\/blog\/#organization"},"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/","url":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/","name":"How do we use nn.parameter in PyTorch? - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/blog\/#website"},"datePublished":"2024-03-16T08:25:14+00:00","dateModified":"2024-03-22T10:56:56+00:00","breadcrumb":{"@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/blog\/how-do-we-use-nn-parameter-in-pytorch\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.silicloud.com\/blog\/"},{"@type":"ListItem","position":2,"name":"How do we use nn.parameter in PyTorch?"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/blog\/#website","url":"https:\/\/www.silicloud.com\/blog\/","name":"Silicon Cloud Blog","description":"","publisher":{"@id":"https:\/\/www.silicloud.com\/blog\/#organization"},"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.silicloud.com\/blog\/#organization","name":"Silicon Cloud Blog","url":"https:\/\/www.silicloud.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.silicloud.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.silicloud.com\/blog\/wp-content\/uploads\/2023\/11\/EN-SILICON-Full.png","contentUrl":"https:\/\/www.silicloud.com\/blog\/wp-content\/uploads\/2023\/11\/EN-SILICON-Full.png","width":1024,"height":1024,"caption":"Silicon Cloud Blog"},"image":{"@id":"https:\/\/www.silicloud.com\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/SiliCloudGlobal\/","https:\/\/twitter.com\/SiliCloudGlobal"]},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/3b041b19cffc258705478ecfab895378","name":"Emily Johnson","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.silicloud.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/a5cb4e73d02ab1d79f2dfe919389ff7c1de072baa97686392031c03d858cc358?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a5cb4e73d02ab1d79f2dfe919389ff7c1de072baa97686392031c03d858cc358?s=96&d=mm&r=g","caption":"Emily Johnson"},"url":"https:\/\/www.silicloud.com\/blog\/author\/emilyjohnson\/"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/posts\/27401","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/comments?post=27401"}],"version-history":[{"count":1,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/posts\/27401\/revisions"}],"predecessor-version":[{"id":61631,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/posts\/27401\/revisions\/61631"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/media?parent=27401"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/categories?post=27401"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/blog\/wp-json\/wp\/v2\/tags?post=27401"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}