{"id":76752,"date":"2024-09-14T19:27:16","date_gmt":"2024-09-14T15:57:16","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/maxpool2d-in-pytorch-4p3e\/"},"modified":"2024-09-14T19:27:16","modified_gmt":"2024-09-14T15:57:16","slug":"maxpool2d-in-pytorch-4p3e","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/maxpool2d-in-pytorch-4p3e\/","title":{"rendered":"MaxPool2d() \u062f\u0631 PyTorch"},"content":{"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<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<p>\u067e\u0633\u062a \u0645\u0646 Pooling Layer \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<p>\u067e\u0633\u062a \u0645\u0646 MaxPool1d() \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0646\u06cc\u0627\u0632_grad \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<p>MaxPool2d() \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 3 \u0628\u0639\u062f\u06cc \u06cc\u0627 4 \u0628\u0639\u062f\u06cc \u06cc\u06a9 \u06cc\u0627 \u0686\u0646\u062f \u0645\u0642\u062f\u0627\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0634\u062f\u0647 \u0628\u0627 \u0627\u062f\u063a\u0627\u0645 \u062d\u062f\u0627\u06a9\u062b\u0631 2 \u0628\u0639\u062f\u06cc \u0631\u0627 \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 3 \u0628\u0639\u062f\u06cc \u06cc\u0627 4 \u0628\u0639\u062f\u06cc \u06cc\u06a9 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u0645\u0627\u0646\u0646\u062f \u0632\u06cc\u0631 \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u062f:<\/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 kernel_size(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:int \u06cc\u0627 tuple \u06cc\u0627 list \u0627\u0632 int). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 1 &lt;= x.<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 stride(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:kernel_size-\u0646\u0648\u0639:int \u06cc\u0627 tuple \u06cc\u0627 list \u0627\u0632 int). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 1 &lt;= x.<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 padding(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:0-\u0646\u0648\u0639:int \u06cc\u0627 tuple \u06cc\u0627 list \u0627\u0632 int). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 0 &lt;= x.<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 dilation(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:1-\u0646\u0648\u0639:int \u06cc\u0627 tuple \u06cc\u0627 list \u0627\u0632 int). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 1 &lt;= x.<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 return_indices(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:False-\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 ceil_mode(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:False-\u0646\u0648\u0639:bool).<br \/>\n\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).<br \/>\n\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 \u0646\u0634\u062f\u0647 \u0627\u0633\u062a True \u062a\u0648\u0633\u0637 MaxPool2d().<\/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>maxpool2d = nn.MaxPool2d(kernel_size=1)<br \/>\ntensor2 = maxpool2d(input=tensor1)<br \/>\ntensor2<br \/>\n# tensor([[[8., -3., 0., 1., 5., -2.]]])<\/p>\n<p>tensor2.requires_grad<br \/>\n# False<\/p>\n<p>maxpool2d<br \/>\n# MaxPool2d(kernel_size=1, stride=1, padding=0, dilation=1, ceil_mode=False)<\/p>\n<p>maxpool2d.kernel_size<br \/>\n# 1<\/p>\n<p>maxpool2d.stride<br \/>\n# 1<\/p>\n<p>maxpool2d.padding<br \/>\n# 0<\/p>\n<p>maxpool2d.dilation<br \/>\n# 1<\/p>\n<p>maxpool2d.return_indices<br \/>\n# False<\/p>\n<p>maxpool2d.ceil_mode<br \/>\n# False<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=1, stride=None, padding=0,<br \/>\n                         dilation=1, return_indices=False, ceil_mode=False)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# tensor([[[8., -3., 0., 1., 5., -2.]]])<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=2, padding=1, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8., 0., 5., -2.]]]), tensor([[[0, 2, 4, 5]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=3, padding=1, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8., 5.]]]), tensor([[[0, 4]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=4, padding=2, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8., 5.]]]), tensor([[[0, 4]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=5, padding=2, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8., 5.]]]), tensor([[[0, 4]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=6, padding=3, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8., 5.]]]), tensor([[[0, 4]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=7, padding=3, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8.]]]), tensor([[[0]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=8, padding=4, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8.]]]), tensor([[[0]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=9, padding=4, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8.]]]), tensor([[[0]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=10, padding=5, return_indices=True)<br \/>\nmaxpool2d(input=tensor1)<br \/>\n# (tensor([[[8.]]]), tensor([[[0]]]))<br \/>\netc.<\/p>\n<p>my_tensor = torch.tensor([[[8., -3., 0.],<br \/>\n                           [1., 5., -2.]]])<br \/>\nmaxpool2d = nn.MaxPool2d(kernel_size=1, return_indices=True)<br \/>\nmaxpool2d(input=my_tensor)<br \/>\n# (tensor([[[8., -3., 0.],<br \/>\n#           [1., 5., -2.]]]),<br \/>\n#  tensor([[[0, 1, 2],<br \/>\n#           [3, 4, 5]]]))<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=2, return_indices=True)<br \/>\nmaxpool2d(input=my_tensor)<br \/>\n# (tensor([[[8.]]]),<br \/>\n#  tensor([[[0]]]))<\/p>\n<p>my_tensor = torch.tensor([[[8.], [-3.], [0.], [1.], [5.], [-2.]]])<\/p>\n<p>maxpool2d = nn.MaxPool2d(kernel_size=1, return_indices=True)<br \/>\nmaxpool2d(input=my_tensor)<br \/>\n# (tensor([[[8.], [-3.], [0.], [1.], [5.], [-2.]]]),<br \/>\n#  tensor([[[0], [1], [2], [3], [4], [5]]]))<\/p>\n<p>my_tensor = torch.tensor([[[[8.], [-3.], [0.]],<br \/>\n                           [[1.], [5.], [-2.]]]])<br \/>\nmaxpool2d = nn.MaxPool2d(kernel_size=1, return_indices=True)<br \/>\nmaxpool2d(input=my_tensor)<br \/>\n# (tensor([[[[8.], [-3.], [0.]],<br \/>\n#           [[1.], [5.], [-2.]]]]),<br \/>\n#  tensor([[[[0], [1], [2]],<br \/>\n#           [[0], [1], [2]]]]))<\/p>\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<ul>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 Pooling Layer \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 MaxPool1d() \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0646\u06cc\u0627\u0632_grad \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/li>\n<\/ul>\n<p>MaxPool2d() \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 3 \u0628\u0639\u062f\u06cc \u06cc\u0627 4 \u0628\u0639\u062f\u06cc \u06cc\u06a9 \u06cc\u0627 \u0686\u0646\u062f \u0645\u0642\u062f\u0627\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0634\u062f\u0647 \u0628\u0627 \u0627\u062f\u063a\u0627\u0645 \u062d\u062f\u0627\u06a9\u062b\u0631 2 \u0628\u0639\u062f\u06cc \u0631\u0627 \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 3 \u0628\u0639\u062f\u06cc \u06cc\u0627 4 \u0628\u0639\u062f\u06cc \u06cc\u06a9 \u06cc\u0627 \u0686\u0646\u062f \u0639\u0646\u0635\u0631 \u0645\u0627\u0646\u0646\u062f \u0632\u06cc\u0631 \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u062f:<\/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>kernel_size<\/code>(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:<code>int<\/code> \u06cc\u0627 <code>tuple<\/code> \u06cc\u0627 <code>list<\/code> \u0627\u0632 <code>int<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>1 &lt;= x<\/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>stride<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>kernel_size<\/code>-\u0646\u0648\u0639:<code>int<\/code> \u06cc\u0627 <code>tuple<\/code> \u06cc\u0627 <code>list<\/code> \u0627\u0632 <code>int<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>1 &lt;= x<\/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>padding<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>0<\/code>-\u0646\u0648\u0639:<code>int<\/code> \u06cc\u0627 <code>tuple<\/code> \u06cc\u0627 <code>list<\/code> \u0627\u0632 <code>int<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>0 &lt;= x<\/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>dilation<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>1<\/code>-\u0646\u0648\u0639:<code>int<\/code> \u06cc\u0627 <code>tuple<\/code> \u06cc\u0627 <code>list<\/code> \u0627\u0632 <code>int<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>1 &lt;= x<\/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>return_indices<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>False<\/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>ceil_mode<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>False<\/code>-\u0646\u0648\u0639:<code>bool<\/code>).<\/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 \u0646\u0634\u062f\u0647 \u0627\u0633\u062a <code>True<\/code> \u062a\u0648\u0633\u0637 <code>MaxPool2d()<\/code>.\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\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/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\">maxpool2d<\/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([[[8., -3., 0., 1., 5., -2.]]])\n<\/span>\n<span class=\"n\">tensor2<\/span><span class=\"p\">.<\/span><span class=\"n\">requires_grad<\/span>\n<span class=\"c1\"># False\n<\/span>\n<span class=\"n\">maxpool2d<\/span>\n<span class=\"c1\"># MaxPool2d(kernel_size=1, stride=1, padding=0, dilation=1, ceil_mode=False)\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">kernel_size<\/span>\n<span class=\"c1\"># 1\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">stride<\/span>\n<span class=\"c1\"># 1\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">padding<\/span>\n<span class=\"c1\"># 0\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">dilation<\/span>\n<span class=\"c1\"># 1\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">return_indices<\/span>\n<span class=\"c1\"># False\n<\/span>\n<span class=\"n\">maxpool2d<\/span><span class=\"p\">.<\/span><span class=\"n\">ceil_mode<\/span>\n<span class=\"c1\"># False\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">stride<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">0<\/span><span class=\"p\">,<\/span> \n                         <span class=\"n\">dilation<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">False<\/span><span class=\"p\">,<\/span> <span class=\"n\">ceil_mode<\/span><span class=\"o\">=<\/span><span class=\"bp\">False<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., -3., 0., 1., 5., -2.]]])\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., 0., 5., -2.]]]), tensor([[[0, 2, 4, 5]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., 5.]]]), tensor([[[0, 4]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., 5.]]]), tensor([[[0, 4]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">5<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., 5.]]]), tensor([[[0, 4]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">6<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., 5.]]]), tensor([[[0, 4]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">7<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.]]]), tensor([[[0]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">8<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.]]]), tensor([[[0]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">9<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.]]]), tensor([[[0]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">10<\/span><span class=\"p\">,<\/span> <span class=\"n\">padding<\/span><span class=\"o\">=<\/span><span class=\"mi\">5<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.]]]), tensor([[[0]]]))\n<\/span><span class=\"n\">etc<\/span><span class=\"p\">.<\/span>\n\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\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8., -3., 0.],\n#           [1., 5., -2.]]]),\n#  tensor([[[0, 1, 2],\n#           [3, 4, 5]]]))\n<\/span>\n<span class=\"n\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.]]]),\n#  tensor([[[0]]]))\n<\/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\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[8.], [-3.], [0.], [1.], [5.], [-2.]]]),\n#  tensor([[[0], [1], [2], [3], [4], [5]]]))\n<\/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\">maxpool2d<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">MaxPool2d<\/span><span class=\"p\">(<\/span><span class=\"n\">kernel_size<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">return_indices<\/span><span class=\"o\">=<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">maxpool2d<\/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([[[[8.], [-3.], [0.]],\n#           [[1.], [5.], [-2.]]]]),\n#  tensor([[[[0], [1], [2]],\n#           [[0], [1], [2]]]]))\n<\/span><\/code><\/pre>\n<\/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: \u067e\u0633\u062a \u0645\u0646 Pooling Layer \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f. \u067e\u0633\u062a \u0645\u0646 MaxPool1d() \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f. \u067e\u0633\u062a \u0645\u0646 \u0646\u06cc\u0627\u0632_grad \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f. MaxPool2d() \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 3 \u0628\u0639\u062f\u06cc \u06cc\u0627 4 \u0628\u0639\u062f\u06cc \u06cc\u06a9 \u06cc\u0627 \u0686\u0646\u062f \u0645\u0642\u062f\u0627\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0634\u062f\u0647 \u0628\u0627 \u0627\u062f\u063a\u0627\u0645 &hellip;<\/p>\n","protected":false},"author":2,"featured_media":0,"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-76752","post","type-post","status-publish","format-standard","hentry","category-dev"],"_links":{"self":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/76752","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=76752"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/76752\/revisions"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=76752"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=76752"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=76752"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}