{"id":73917,"date":"2024-08-18T20:35:14","date_gmt":"2024-08-18T17:05:14","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/bceloss-in-pytorch-3m4d\/"},"modified":"2024-08-18T20:35:14","modified_gmt":"2024-08-18T17:05:14","slug":"bceloss-in-pytorch-3m4d","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/bceloss-in-pytorch-3m4d\/","title":{"rendered":"BCEloss() \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>()BCEloss \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0627\u0632 \u0645\u0642\u0627\u062f\u06cc\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f.float) \u062a\u0648\u0633\u0637 BCE Loss \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D \u0627\u0632 \u0639\u0646\u0627\u0635\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc \u0634\u0648\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 weight(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:None-\u0646\u0648\u0639:tensor \u0627\u0632 int\u060c float \u06cc\u0627 bool). \u0627\u06af\u0631 \u062f\u0627\u062f\u0647 \u0646\u0634\u0648\u062f\u060c \u0627\u06cc\u0646 \u0627\u0633\u062a 1.<br \/>\n\u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f reduction \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 (\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:&#8217;mean&#8217;-\u0646\u0648\u0639:str). *&#8217;none&#8217;\u060c &#8216;mean&#8217; \u06cc\u0627 &#8216;sum&#8217; \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0646\u062a\u062e\u0627\u0628 \u06a9\u0631\u062f.<br \/>\n\u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f size_average \u0648 reduce \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0627\u0648\u0644\u06cc\u0647 \u0633\u0627\u0632\u06cc \u0627\u0645\u0627 \u0645\u0646\u0633\u0648\u062e \u0634\u062f\u0647 \u0627\u0646\u062f.<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). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 0.<br \/>\n\u0627\u0633\u062a\u062f\u0644\u0627\u0644 \u062f\u0648\u0645 \u0627\u06cc\u0646 \u0627\u0633\u062a target(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:tensor \u0627\u0632 float). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f 0.<\/p>\n<p>input  \u0648 target \u0628\u0627\u06cc\u062f \u06cc\u06a9 \u0627\u0646\u062f\u0627\u0632\u0647 \u0628\u0627\u0634\u062f \u062f\u0631 \u063a\u06cc\u0631 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u06cc\u06a9 \u0647\u0634\u062f\u0627\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.<br \/>\n1D \u062e\u0627\u0644\u06cc \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D input \u0648 target \u062a\u0627\u0646\u0633\u0648\u0631\u0647\u0627 \u0628\u0627 reduction=&#8217;mean&#8217; \u0628\u0627\u0632\u06af\u0634\u062a nan.<br \/>\n1D \u062e\u0627\u0644\u06cc \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D input \u0648 target \u062a\u0627\u0646\u0633\u0648\u0631\u0647\u0627 \u0628\u0627 reduction=&#8217;sum&#8217; \u0628\u0627\u0632\u06af\u0634\u062a 0..<\/p>\n<p>import torch<br \/>\nfrom torch import nn<\/p>\n<p>tensor1 = torch.tensor([0.4, 0.8, 0.6, 0.3, 0.0, 0.5])<br \/>\ntensor2 = torch.tensor([0.2, 0.9, 0.4, 0.1, 0.8, 0.5])<br \/>\n                   # -w(y*logx+(1-y)*log(1-x)))<br \/>\n                   # -1(0.2*log0.4+(1-0.2)*log(1-0.4))<br \/>\n                   # \u2193\u2193\u2193\u2193\u2193\u2193<br \/>\n                   # 0.5919+0.3618+0.7541+0.4414+80.0+0.6931 = 82.8423<br \/>\n                   # 82.8423 \/ 6 = 13.8071<br \/>\nbceloss = nn.BCELoss()<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(7.2500)<\/p>\n<p>bceloss<br \/>\n# BCELoss()<\/p>\n<p>bceloss.reduction<br \/>\n# &#8216;mean&#8217;<\/p>\n<p>print(bceloss.weight)<br \/>\n# None<\/p>\n<p>bceloss = nn.BCELoss(weight=None, reduction=&#8217;mean&#8217;)<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(13.8071)<\/p>\n<p>bceloss = nn.BCELoss(weight=None, reduction=&#8217;sum&#8217;)<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(82.8423)<\/p>\n<p>bceloss = nn.BCELoss(weight=None, reduction=&#8217;none&#8217;)<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor([0.5919, 0.3618, 0.7541, 0.4414, 80.0000, 0.6931])<\/p>\n<p>bceloss = nn.BCELoss(weight=torch.tensor([0., 1., 2., 3., 4., 5.]))<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(54.4433)<\/p>\n<p>bceloss = nn.BCELoss(weight=torch.tensor([0.]))<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(0.)<\/p>\n<p>bceloss = nn.BCELoss(weight=torch.tensor([0, 1, 2, 3, 4, 5]))<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(54.4433)<\/p>\n<p>bceloss = nn.BCELoss(weight=torch.tensor([0]))<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(0.)<\/p>\n<p>bceloss = nn.BCELoss(<br \/>\n              weight=torch.tensor([True, False, True, False, True, False])<br \/>\n          )<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(13.5577)<\/p>\n<p>bceloss = nn.BCELoss(weight=torch.tensor([False]))<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(0.)<\/p>\n<p>tensor1 = torch.tensor([[0.4, 0.8, 0.6], [0.3, 0.0, 0.5]])<br \/>\ntensor2 = torch.tensor([[0.2, 0.9, 0.4], [0.1, 0.8, 0.5]])<\/p>\n<p>bceloss = nn.BCELoss()<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(13.8071)<\/p>\n<p>tensor1 = torch.tensor([[[0.4], [0.8], [0.6]], [[0.3], [0.0], [0.5]]])<br \/>\ntensor2 = torch.tensor([[[0.2], [0.9], [0.4]], [[0.1], [0.8], [0.5]]])<\/p>\n<p>bceloss = nn.BCELoss()<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(13.8071)<\/p>\n<p>tensor1 = torch.tensor([])<br \/>\ntensor2 = torch.tensor([])<\/p>\n<p>bceloss = nn.BCELoss(reduction=&#8217;mean&#8217;)<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(nan)<\/p>\n<p>bceloss = nn.BCELoss(reduction=&#8217;sum&#8217;)<br \/>\nbceloss(input=tensor1, target=tensor2)<br \/>\n# tensor(0.)<\/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=\"1964178\" 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>()BCEloss \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0627\u0632 \u0645\u0642\u0627\u062f\u06cc\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f.<code>float<\/code>) \u062a\u0648\u0633\u0637 BCE Loss \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D \u0627\u0632 \u0639\u0646\u0627\u0635\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc \u0634\u0648\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>weight<\/code>(\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>None<\/code>-\u0646\u0648\u0639:<code>tensor<\/code> \u0627\u0632 <code>int<\/code>\u060c <code>float<\/code> \u06cc\u0627 <code>bool<\/code>). \u0627\u06af\u0631 \u062f\u0627\u062f\u0647 \u0646\u0634\u0648\u062f\u060c \u0627\u06cc\u0646 \u0627\u0633\u062a <code>1<\/code>.<\/li>\n<li>\u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f <code>reduction<\/code> \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631\u062f\u0647\u06cc \u0627\u0648\u0644\u06cc\u0647 (\u0627\u062e\u062a\u06cc\u0627\u0631\u06cc-\u067e\u06cc\u0634 \u0641\u0631\u0636:<code>'mean'<\/code>-\u0646\u0648\u0639:<code>str<\/code>). *<code>'none'<\/code>\u060c <code>'mean'<\/code> \u06cc\u0627 <code>'sum'<\/code> \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0627\u0646\u062a\u062e\u0627\u0628 \u06a9\u0631\u062f.<\/li>\n<li>\u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f <code>size_average<\/code> \u0648 <code>reduce<\/code> \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0627\u0648\u0644\u06cc\u0647 \u0633\u0627\u0632\u06cc \u0627\u0645\u0627 \u0645\u0646\u0633\u0648\u062e \u0634\u062f\u0647 \u0627\u0646\u062f.<\/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>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>0.<\/code><\/li>\n<li>\u0627\u0633\u062a\u062f\u0644\u0627\u0644 \u062f\u0648\u0645 \u0627\u06cc\u0646 \u0627\u0633\u062a <code>target<\/code>(\u0627\u0644\u0632\u0627\u0645\u06cc-\u0646\u0648\u0639:<code>tensor<\/code> \u0627\u0632 <code>float<\/code>). *\u0628\u0627\u06cc\u062f \u0628\u0627\u0634\u062f <code>0.<\/code><\/li>\n<li>\n<code>input<\/code>  \u0648 <code>target<\/code> \u0628\u0627\u06cc\u062f \u06cc\u06a9 \u0627\u0646\u062f\u0627\u0632\u0647 \u0628\u0627\u0634\u062f \u062f\u0631 \u063a\u06cc\u0631 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u06cc\u06a9 \u0647\u0634\u062f\u0627\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.<\/li>\n<li>1D \u062e\u0627\u0644\u06cc \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D <code>input<\/code> \u0648 <code>target<\/code> \u062a\u0627\u0646\u0633\u0648\u0631\u0647\u0627 \u0628\u0627 <code>reduction='mean'<\/code> \u0628\u0627\u0632\u06af\u0634\u062a <code>nan<\/code>.<\/li>\n<li>1D \u062e\u0627\u0644\u06cc \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D <code>input<\/code> \u0648 <code>target<\/code> \u062a\u0627\u0646\u0633\u0648\u0631\u0647\u0627 \u0628\u0627 <code>reduction='sum'<\/code> \u0628\u0627\u0632\u06af\u0634\u062a <code>0.<\/code>.<br \/>\n\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\">0.4<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.8<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.6<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.3<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.5<\/span><span class=\"p\">])<\/span>\n<span class=\"n\">tensor2<\/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\">0.2<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.9<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.4<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.1<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.8<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.5<\/span><span class=\"p\">])<\/span>\n                   <span class=\"c1\"># -w(y*logx+(1-y)*log(1-x)))\n<\/span>                   <span class=\"c1\"># -1(0.2*log0.4+(1-0.2)*log(1-0.4))\n<\/span>                   <span class=\"c1\"># \u2193\u2193\u2193\u2193\u2193\u2193\n<\/span>                   <span class=\"c1\"># 0.5919+0.3618+0.7541+0.4414+80.0+0.6931 = 82.8423\n<\/span>                   <span class=\"c1\"># 82.8423 \/ 6 = 13.8071\n<\/span><span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">()<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(7.2500)\n<\/span>\n<span class=\"n\">bceloss<\/span>\n<span class=\"c1\"># BCELoss()\n<\/span>\n<span class=\"n\">bceloss<\/span><span class=\"p\">.<\/span><span class=\"n\">reduction<\/span>\n<span class=\"c1\"># 'mean'\n<\/span>\n<span class=\"nf\">print<\/span><span class=\"p\">(<\/span><span class=\"n\">bceloss<\/span><span class=\"p\">.<\/span><span class=\"n\">weight<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># None\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">,<\/span> <span class=\"n\">reduction<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">mean<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(13.8071)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">,<\/span> <span class=\"n\">reduction<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">sum<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(82.8423)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">,<\/span> <span class=\"n\">reduction<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">none<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor([0.5919, 0.3618, 0.7541, 0.4414, 80.0000, 0.6931])\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/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\">0.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">1.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">2.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">3.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">4.<\/span><span class=\"p\">,<\/span> <span class=\"mf\">5.<\/span><span class=\"p\">]))<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(54.4433)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/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\">0.<\/span><span class=\"p\">]))<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(0.)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/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=\"mi\">0<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"mi\">4<\/span><span class=\"p\">,<\/span> <span class=\"mi\">5<\/span><span class=\"p\">]))<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(54.4433)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/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=\"mi\">0<\/span><span class=\"p\">]))<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(0.)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span>\n              <span class=\"n\">weight<\/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=\"bp\">True<\/span><span class=\"p\">,<\/span> <span class=\"bp\">False<\/span><span class=\"p\">,<\/span> <span class=\"bp\">True<\/span><span class=\"p\">,<\/span> <span class=\"bp\">False<\/span><span class=\"p\">,<\/span> <span class=\"bp\">True<\/span><span class=\"p\">,<\/span> <span class=\"bp\">False<\/span><span class=\"p\">])<\/span>\n          <span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(13.5577)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">weight<\/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=\"bp\">False<\/span><span class=\"p\">]))<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(0.)\n<\/span>\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\">0.4<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.8<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.6<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.3<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.0<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.5<\/span><span class=\"p\">]])<\/span>\n<span class=\"n\">tensor2<\/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\">0.2<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.9<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.4<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.1<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.8<\/span><span class=\"p\">,<\/span> <span class=\"mf\">0.5<\/span><span class=\"p\">]])<\/span>\n\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">()<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(13.8071)\n<\/span>\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\">0.4<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.8<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.6<\/span><span class=\"p\">]],<\/span> <span class=\"p\">[[<\/span><span class=\"mf\">0.3<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.0<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.5<\/span><span class=\"p\">]]])<\/span>\n<span class=\"n\">tensor2<\/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\">0.2<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.9<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.4<\/span><span class=\"p\">]],<\/span> <span class=\"p\">[[<\/span><span class=\"mf\">0.1<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.8<\/span><span class=\"p\">],<\/span> <span class=\"p\">[<\/span><span class=\"mf\">0.5<\/span><span class=\"p\">]]])<\/span>\n\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">()<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(13.8071)\n<\/span>\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>\n<span class=\"n\">tensor2<\/span> <span class=\"o\">=<\/span> <span class=\"n\">torch<\/span><span class=\"p\">.<\/span><span class=\"nf\">tensor<\/span><span class=\"p\">([])<\/span>\n\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">reduction<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">mean<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(nan)\n<\/span>\n<span class=\"n\">bceloss<\/span> <span class=\"o\">=<\/span> <span class=\"n\">nn<\/span><span class=\"p\">.<\/span><span class=\"nc\">BCELoss<\/span><span class=\"p\">(<\/span><span class=\"n\">reduction<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">sum<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">bceloss<\/span><span class=\"p\">(<\/span><span class=\"nb\">input<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor1<\/span><span class=\"p\">,<\/span> <span class=\"n\">target<\/span><span class=\"o\">=<\/span><span class=\"n\">tensor2<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># tensor(0.)\n<\/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: ()BCEloss \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0627\u0632 \u0645\u0642\u0627\u062f\u06cc\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u062f.float) \u062a\u0648\u0633\u0637 BCE Loss \u0627\u0632 \u062a\u0627\u0646\u0633\u0648\u0631 0D \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 D \u0627\u0632 \u0639\u0646\u0627\u0635\u0631 \u0635\u0641\u0631 \u06cc\u0627 \u0628\u06cc\u0634\u062a\u0631 \u0645\u062d\u0627\u0633\u0628\u0647 \u0645\u06cc \u0634\u0648\u062f \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a: &hellip;<\/p>\n","protected":false},"author":2,"featured_media":73918,"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-73917","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\/73917","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=73917"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/73917\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media\/73918"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=73917"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=73917"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=73917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}