{"id":76921,"date":"2024-09-16T14:12:31","date_gmt":"2024-09-16T10:42:31","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/batchnorm2d-in-pytorch-1de4\/"},"modified":"2024-09-16T14:12:31","modified_gmt":"2024-09-16T10:42:31","slug":"batchnorm2d-in-pytorch-1de4","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/batchnorm2d-in-pytorch-1de4\/","title":{"rendered":"BatchNorm2d() \u062f\u0631 PyTorch &#8211; \u0627\u0646\u062c\u0645\u0646 DEV"},"content":{"rendered":"<p>Summarize this content to 400 words in Persian Lang<br \/>\n            \u0628\u0631\u0627\u06cc \u0645\u0646 \u06cc\u06a9 \u0642\u0647\u0648\u0647 \u0628\u062e\u0631\u2615<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>BatchNorm2d() \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u0631\u0627 \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0646\u0631\u0645\u0627\u0644\u200c\u0633\u0627\u0632\u06cc \u062f\u0633\u062a\u0647\u200c\u0627\u06cc 2 \u0628\u0639\u062f\u06cc \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f\u060c \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0627\u0648\u0644 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a num_features(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:int). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 1 .<br \/>\n\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u062f\u0648\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a eps(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:1e-05-\u0646\u0648\u0639:float).<br \/>\n\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0633\u0648\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a momentum(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:0.1-\u0646\u0648\u0639:float).<br \/>\n\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0686\u0647\u0627\u0631\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a affine(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:True-\u0646\u0648\u0639:bool).<br \/>\n\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u067e\u0646\u062c\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a track_running_stats(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:True-\u0646\u0648\u0639:bool).<br \/>\n\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0634\u0634\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a device(\u0646\u0648\u0639 \u0627\u062e\u062a\u06cc\u0627\u0631\u06cc:str\u060c int \u06cc\u0627 \u062f\u0633\u062a\u06af\u0627\u0647()). *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0647\u0641\u062a\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a dtype(\u0646\u0648\u0639 \u0627\u062e\u062a\u06cc\u0627\u0631\u06cc:int). *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>\u0627\u0633\u062a\u062f\u0644\u0627\u0644 \u0627\u0648\u0644 \u0627\u06cc\u0646 \u0627\u0633\u062a input(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:tensor \u0627\u0632 float).<\/p>\n<p>\u062a\u0627\u0646\u0633\u0648\u0631 requires_grad \u06a9\u0647 \u0647\u0633\u062a False \u0628\u0647 \u0637\u0648\u0631 \u067e\u06cc\u0634 \u0641\u0631\u0636 \u0631\u0648\u06cc \u062a\u0646\u0638\u06cc\u0645 \u0634\u062f\u0647 \u0627\u0633\u062a True \u062a\u0648\u0633\u0637 BatchNorm2d().<\/p>\n<p>\u062a\u0627\u0646\u0633\u0648\u0631 \u0648\u0631\u0648\u062f\u06cc device \u0648 dtype \u0628\u0627\u06cc\u062f \u0647\u0645\u0627\u0646 \u0628\u0627\u0634\u062f BatchNorm2d()&#39;s device \u0648 dtype \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628.<\/p>\n<p>batchnorm2d1.device  \u0648 batchnorm2d1.dtype \u06a9\u0627\u0631 \u0646\u06a9\u0646<\/p>\n<p>import torch<br \/>\nfrom torch import nn<\/p>\n<p>tensor1 = torch.tensor([[[[8., -3., 0., 1., 5., -2.]]]])<\/p>\n<p>tensor1.requires_grad<br \/>\n# False<\/p>\n<p>batchnorm2d1 = nn.BatchNorm2d(num_features=1)<br \/>\ntensor2 = batchnorm2d1(input=tensor1)<br \/>\ntensor2<br \/>\n# tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>tensor2.requires_grad<br \/>\n# True<\/p>\n<p>batchnorm2d1<br \/>\n# BatchNorm2d(1, eps=1e-05, momentum=0.1, affine=True,<br \/>\n#             track_running_stats=True)<\/p>\n<p>batchnorm2d1.num_features<br \/>\n# 1<\/p>\n<p>batchnorm2d1.eps<br \/>\n# 1e-05<\/p>\n<p>batchnorm2d1.momentum<br \/>\n# 0.1<\/p>\n<p>batchnorm2d1.affine<br \/>\n# True<\/p>\n<p>batchnorm2d1.track_running_stats<br \/>\n# True<\/p>\n<p>batchnorm2d2 = nn.BatchNorm2d(num_features=1)<br \/>\nbatchnorm2d2(input=tensor2)<br \/>\n# tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>batchnorm2d = nn.BatchNorm2d(num_features=1, eps=1e-05, momentum=0.1,<br \/>\n                             affine=True, track_running_stats=True,<br \/>\n                             device=None, dtype=None)<br \/>\nbatchnorm2d(input=tensor1)<br \/>\n# tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>my_tensor = torch.tensor([[[[8., -3., 0.],<br \/>\n                            [1., 5., -2.]]]])<br \/>\nbatchnorm2d = nn.BatchNorm2d(num_features=1)<br \/>\nbatchnorm2d(input=my_tensor)<br \/>\n# tensor([[[[1.6830, -1.1651, -0.3884],<br \/>\n#           [-0.1295, 0.9062, -0.9062]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>my_tensor = torch.tensor([[[[8.], [-3.], [0.], [1.], [5.], [-2.]]]])<\/p>\n<p>batchnorm2d = nn.BatchNorm2d(num_features=1)<br \/>\nbatchnorm2d(input=my_tensor)<br \/>\n# tensor([[[[1.6830], [-1.1651], [-0.3884], [-0.1295], [0.9062], [-0.9062]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>my_tensor = torch.tensor([[[[8.], [-3.], [0.]],<br \/>\n                           [[1.], [5.], [-2.]]]])<br \/>\nbatchnorm2d = nn.BatchNorm2d(num_features=2)<br \/>\nbatchnorm2d(input=my_tensor)<br \/>\n# tensor([[[[1.3641], [-1.0051], [-0.3590]],<br \/>\n#          [[-0.1162], [1.2787], [-1.1625]]]],<br \/>\n#        grad_fn=)<\/p>\n<p>    \u0648\u0627\u0631\u062f \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u0634\u0648\u06cc\u062f<\/p>\n<p>    \u0627\u0632 \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u062e\u0627\u0631\u062c \u0634\u0648\u06cc\u062f<\/p>\n<div data-article-id=\"2002277\" id=\"article-body\">\n<p>\u0628\u0631\u0627\u06cc \u0645\u0646 \u06cc\u06a9 \u0642\u0647\u0648\u0647 \u0628\u062e\u0631\u2615<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>BatchNorm2d() \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u0631\u0627 \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0646\u0631\u0645\u0627\u0644\u200c\u0633\u0627\u0632\u06cc \u062f\u0633\u062a\u0647\u200c\u0627\u06cc 2 \u0628\u0639\u062f\u06cc \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f\u060c \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<ul>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0627\u0648\u0644 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>num_features<\/code>(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:<code>int<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>1 .<\/code><\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u062f\u0648\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>eps<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>1e-05<\/code>-\u0646\u0648\u0639:<code>float<\/code>).<\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0633\u0648\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>momentum<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>0.1<\/code>-\u0646\u0648\u0639:<code>float<\/code>).<\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0686\u0647\u0627\u0631\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>affine<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>True<\/code>-\u0646\u0648\u0639:<code>bool<\/code>).<\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u067e\u0646\u062c\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>track_running_stats<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>True<\/code>-\u0646\u0648\u0639:<code>bool<\/code>).<\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0634\u0634\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>device<\/code>(\u0646\u0648\u0639 \u0627\u062e\u062a\u06cc\u0627\u0631\u06cc:<code>str<\/code>\u060c <code>int<\/code> \u06cc\u0627 \u062f\u0633\u062a\u06af\u0627\u0647()). *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:\n<\/li>\n<li>\u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0647\u0641\u062a\u0645 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 \u0627\u0633\u062a <code>dtype<\/code>(\u0646\u0648\u0639 \u0627\u062e\u062a\u06cc\u0627\u0631\u06cc:<code>int<\/code>). *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:\n<\/li>\n<li>\u0627\u0633\u062a\u062f\u0644\u0627\u0644 \u0627\u0648\u0644 \u0627\u06cc\u0646 \u0627\u0633\u062a <code>input<\/code>(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:<code>tensor<\/code> \u0627\u0632 <code>float<\/code>).<\/li>\n<li>\u062a\u0627\u0646\u0633\u0648\u0631 <code>requires_grad<\/code> \u06a9\u0647 \u0647\u0633\u062a <code>False<\/code> \u0628\u0647 \u0637\u0648\u0631 \u067e\u06cc\u0634 \u0641\u0631\u0636 \u0631\u0648\u06cc \u062a\u0646\u0638\u06cc\u0645 \u0634\u062f\u0647 \u0627\u0633\u062a <code>True<\/code> \u062a\u0648\u0633\u0637 <code>BatchNorm2d()<\/code>.<\/li>\n<li>\u062a\u0627\u0646\u0633\u0648\u0631 \u0648\u0631\u0648\u062f\u06cc <code>device<\/code> \u0648 <code>dtype<\/code> \u0628\u0627\u06cc\u062f \u0647\u0645\u0627\u0646 \u0628\u0627\u0634\u062f <code>BatchNorm2d()<\/code>&#39;s <code>device<\/code> \u0648 <code>dtype<\/code> \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628.<\/li>\n<li>\n<code>batchnorm2d1.device<\/code>  \u0648 <code>batchnorm2d1.dtype<\/code> \u06a9\u0627\u0631 \u0646\u06a9\u0646\n<\/li>\n<\/ul>\n<div class=\"highlight js-code-highlight\">\n<pre class=\"highlight python\"><code><span class=\"kn\">import<\/span> <span class=\"n\">torch<\/span>\n<span class=\"kn\">from<\/span> <span class=\"n\">torch<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">nn<\/span>\n\n<span class=\"n\">tensor1<\/span> <span class=\"o\">=<\/span> <span class=\"n\">torch<\/span><span class=\"p\">.<\/span><span class=\"nf\">tensor<\/span><span class=\"p\">([[[[<\/span><span class=\"mf\">8.<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mf\">3.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">1.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">5.<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mf\">2.<\/span><span class=\"p\">]]]])<\/span>\n\n<span class=\"n\">tensor1<\/span><span class=\"p\">.<\/span><span class=\"n\">requires_grad<\/span>\n<span class=\"c1\"># False\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\n<span class=\"n\">tensor2<\/span> <span class=\"o\">=<\/span> <span class=\"nf\">batchnorm2d1<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">)<\/span>\n<span class=\"n\">tensor2<\/span>\n<span class=\"c1\"># tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span>\n<span class=\"n\">tensor2<\/span><span class=\"p\">.<\/span><span class=\"n\">requires_grad<\/span>\n<span class=\"c1\"># True\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span>\n<span class=\"c1\"># BatchNorm2d(1, eps=1e-05, momentum=0.1, affine=True,\n#             track_running_stats=True)\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span><span class=\"p\">.<\/span><span class=\"n\">num_features<\/span>\n<span class=\"c1\"># 1\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span><span class=\"p\">.<\/span><span class=\"n\">eps<\/span>\n<span class=\"c1\"># 1e-05\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span><span class=\"p\">.<\/span><span class=\"n\">momentum<\/span>\n<span class=\"c1\"># 0.1\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span><span class=\"p\">.<\/span><span class=\"n\">affine<\/span>\n<span class=\"c1\"># True\n<\/span>\n<span class=\"n\">batchnorm2d1<\/span><span class=\"p\">.<\/span><span class=\"n\">track_running_stats<\/span>\n<span class=\"c1\"># True\n<\/span>\n<span class=\"n\">batchnorm2d2<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">batchnorm2d2<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span>\n<span class=\"n\">batchnorm2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">eps<\/span><span class=\"o\">=<\/span><span class=\"mf\">1e-05<\/span><span class=\"p\">,<\/span> <span class=\"n\">momentum<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.1<\/span><span class=\"p\">,<\/span> \n                             <span class=\"n\">affine<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">,<\/span> <span class=\"n\">track_running_stats<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">,<\/span> \n                             <span class=\"n\">device<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">,<\/span> <span class=\"n\">dtype<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">batchnorm2d<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([[[[1.6830, -1.1651, -0.3884, -0.1295, 0.9062, -0.9062]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span>\n<span class=\"n\">my_tensor<\/span> <span class=\"o\">=<\/span> <span class=\"n\">torch<\/span><span class=\"p\">.<\/span><span class=\"nf\">tensor<\/span><span class=\"p\">([[[[<\/span><span class=\"mf\">8.<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mf\">3.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.<\/span><span class=\"p\">],<\/span>\n                            <span class=\"p\">[<\/span><span class=\"mf\">1.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">5.<\/span><span class=\"p\">,<\/span> <span class=\"o\">-<\/span><span class=\"mf\">2.<\/span><span class=\"p\">]]]])<\/span>\n<span class=\"n\">batchnorm2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">batchnorm2d<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">my_tensor<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([[[[1.6830, -1.1651, -0.3884],\n#           [-0.1295, 0.9062, -0.9062]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span>\n<span class=\"n\">my_tensor<\/span> <span class=\"o\">=<\/span> <span class=\"n\">torch<\/span><span class=\"p\">.<\/span><span class=\"nf\">tensor<\/span><span class=\"p\">([[[[<\/span><span class=\"mf\">8.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mf\">3.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">1.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">5.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mf\">2.<\/span><span class=\"p\">]]]])<\/span>\n\n<span class=\"n\">batchnorm2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">batchnorm2d<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">my_tensor<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([[[[1.6830], [-1.1651], [-0.3884], [-0.1295], [0.9062], [-0.9062]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span>\n<span class=\"n\">my_tensor<\/span> <span class=\"o\">=<\/span> <span class=\"n\">torch<\/span><span class=\"p\">.<\/span><span class=\"nf\">tensor<\/span><span class=\"p\">([[[[<\/span><span class=\"mf\">8.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mf\">3.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.<\/span><span class=\"p\">]],<\/span>\n                           <span class=\"p\">[[<\/span><span class=\"mf\">1.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">5.<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"o\">-<\/span><span class=\"mf\">2.<\/span><span class=\"p\">]]]])<\/span>\n<span class=\"n\">batchnorm2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BatchNorm2d<\/span><span class=\"p\">(<\/span><span class=\"n\">num_features<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">batchnorm2d<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">my_tensor<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([[[[1.3641], [-1.0051], [-0.3590]],\n#          [[-0.1162], [1.2787], [-1.1625]]]],\n#        grad_fn=<nativebatchnormbackward0>)\n<\/nativebatchnormbackward0><\/span><\/code><\/pre>\n<div class=\"highlight__panel js-actions-panel\">\n<div class=\"highlight__panel-action js-fullscreen-code-action\">\n    <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" class=\"highlight-action crayons-icon highlight-action--fullscreen-on\"><title>\u0648\u0627\u0631\u062f \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u0634\u0648\u06cc\u062f<\/title>\n    <path d=\"M16 3h6v6h-2V5h-4V3zM2 3h6v2H4v4H2V3zm18 16v-4h2v6h-6v-2h4zM4 19h4v2H2v-6h2v4z\"\/>\n<\/svg><\/p>\n<p>    <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" class=\"highlight-action crayons-icon highlight-action--fullscreen-off\"><title>\u0627\u0632 \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u062e\u0627\u0631\u062c \u0634\u0648\u06cc\u062f<\/title>\n    <path d=\"M18 7h4v2h-6V3h2v4zM8 9H2V7h4V3h2v6zm10 8v4h-2v-6h6v2h-4zM8 15v6H6v-4H2v-2h6z\"\/>\n<\/svg><\/p>\n<\/div>\n<\/div>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Summarize this content to 400 words in Persian Lang \u0628\u0631\u0627\u06cc \u0645\u0646 \u06cc\u06a9 \u0642\u0647\u0648\u0647 \u0628\u062e\u0631\u2615 *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627: BatchNorm2d() \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u0631\u0627 \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0646\u0631\u0645\u0627\u0644\u200c\u0633\u0627\u0632\u06cc \u062f\u0633\u062a\u0647\u200c\u0627\u06cc 2 \u0628\u0639\u062f\u06cc \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f\u060c \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 4 \u0628\u0639\u062f\u06cc \u062f\u0648 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a: *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627: \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0627\u0648\u0644 &hellip;<\/p>\n","protected":false},"author":2,"featured_media":76922,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[339],"tags":[],"class_list":["post-76921","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-dev"],"_links":{"self":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/76921","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/comments?post=76921"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/76921\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media\/76922"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=76921"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=76921"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=76921"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}