{"id":88201,"date":"2026-07-31T17:32:45","date_gmt":"2026-07-31T09:32:45","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/88201.html"},"modified":"2026-07-31T17:32:45","modified_gmt":"2026-07-31T09:32:45","slug":"pytorch-%e6%b7%b1%e5%ba%a6%e5%ad%a6%e4%b9%a0%e7%ac%94%e8%ae%b0%ef%bc%88%e4%b8%89%ef%bc%89pytorch-%e5%bc%a0%e9%87%8f%e5%9f%ba%e7%a1%80-%e4%bb%8e%e9%9b%b6%e5%bc%80%e5%a7%8b%e6%8e%8c","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/88201.html","title":{"rendered":"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor"},"content":{"rendered":"<p>\u7cfb\u5217\u5bfc\u8bfb&#xff1a;\u672c\u7cfb\u5217\u5171 6 \u7bc7&#xff0c;\u4ece PyTorch \u6846\u67b6\u5165\u95e8\u5230\u5b9e\u6218\u6848\u4f8b&#xff0c;\u5e26\u4f60\u7cfb\u7edf\u638c\u63e1\u6df1\u5ea6\u5b66\u4e60\u5f00\u53d1\u3002\u4e0a\u4e00\u7bc7&#xff1a;PyTorch \u4f18\u52bf\u5168\u89e3\u6790\u2014\u2014\u4e3a\u4ec0\u4e48\u79d1\u7814\u548c\u5de5\u4e1a\u90fd\u7231\u5b83<\/p>\n<h3>\u4e00\u3001\u4ec0\u4e48\u662f\u5f20\u91cf&#xff08;Tensor&#xff09;<\/h3>\n<h4>1.1 \u5f20\u91cf\u662f PyTorch \u7684\u6838\u5fc3<\/h4>\n<p>\u5f20\u91cf\u662f PyTorch \u4e2d\u6700\u6838\u5fc3\u7684\u6570\u636e\u62bd\u8c61&#xff0c;\u53ef\u4ee5\u7406\u89e3\u4e3a&#xff1a;<\/p>\n<ul>\n<li>\u5143\u7d20\u4e3a\u540c\u4e00\u79cd\u6570\u636e\u7c7b\u578b\u7684\u591a\u7ef4\u77e9\u9635<\/li>\n<li>\u4e0e NumPy \u6570\u7ec4\u7c7b\u4f3c&#xff0c;\u4f46\u652f\u6301 GPU \u52a0\u901f\u548c\u81ea\u52a8\u5fae\u5206<\/li>\n<li>\u4ee5&#034;\u7c7b&#034;\u7684\u5f62\u5f0f\u5c01\u88c5&#xff0c;\u5185\u7f6e\u4e30\u5bcc\u7684\u8fd0\u7b97\u548c\u65b9\u6cd5<\/li>\n<\/ul>\n<h4>1.2 \u5f20\u91cf\u7684\u7ef4\u5ea6&#xff08;\u9636&#xff09;<\/h4>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/07\/20260731093243-6a6c6bbb61a07.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<p>\u5f20\u91cf\u7684\u7ef4\u5ea6\u6570\u91cf\u79f0\u4e3a\u9636&#xff08;Rank&#xff09;\u6216\u7ef4\u6570&#xff0c;\u901a\u8fc7 ndim \u5c5e\u6027\u67e5\u770b&#xff1a;<\/p>\n<table>\n<tr>\u9636\u6570\u540d\u79f0\u793a\u4f8b\u5f62\u72b6<\/tr>\n<tbody>\n<tr>\n<td align=\"center\">0<\/td>\n<td align=\"left\">\u6807\u91cf&#xff08;Scalar&#xff09;<\/td>\n<td align=\"left\">torch.tensor(5)<\/td>\n<td align=\"left\">[]<\/td>\n<\/tr>\n<tr>\n<td align=\"center\">1<\/td>\n<td align=\"left\">\u5411\u91cf&#xff08;Vector&#xff09;<\/td>\n<td align=\"left\">torch.tensor([1, 2, 3])<\/td>\n<td align=\"left\">[3]<\/td>\n<\/tr>\n<tr>\n<td align=\"center\">2<\/td>\n<td align=\"left\">\u77e9\u9635&#xff08;Matrix&#xff09;<\/td>\n<td align=\"left\">torch.tensor([[1,2],[3,4]])<\/td>\n<td align=\"left\">[2, 2]<\/td>\n<\/tr>\n<tr>\n<td align=\"center\">3<\/td>\n<td align=\"left\">\u4e09\u7ef4\u5f20\u91cf<\/td>\n<td align=\"left\">\u4e00\u5f20\u5f69\u8272\u56fe\u7247 [C, H, W]<\/td>\n<td align=\"left\">[3, 224, 224]<\/td>\n<\/tr>\n<tr>\n<td align=\"center\">4<\/td>\n<td align=\"left\">\u56db\u7ef4\u5f20\u91cf<\/td>\n<td align=\"left\">\u4e00\u4e2a\u6279\u6b21\u56fe\u7247 [B, C, H, W]<\/td>\n<td align=\"left\">[64, 3, 224, 224]<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><span class=\"token keyword\">import<\/span> torch<\/p>\n<p><span class=\"token comment\"># 0 \u9636\u5f20\u91cf&#xff08;\u6807\u91cf&#xff09;<\/span><br \/>\nx0 <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;x0: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x0<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u9636\u6570: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x0<span class=\"token punctuation\">.<\/span>ndim<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u5f62\u72b6: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x0<span class=\"token punctuation\">.<\/span>size<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># \u8f93\u51fa&#xff1a;x0: 2, \u9636\u6570: 0, \u5f62\u72b6: torch.Size([])<\/span><\/p>\n<p><span class=\"token comment\"># 1 \u9636\u5f20\u91cf&#xff08;\u5411\u91cf&#xff09;<\/span><br \/>\nx1 <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u9636\u6570: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x1<span class=\"token punctuation\">.<\/span>ndim<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u5f62\u72b6: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x1<span class=\"token punctuation\">.<\/span>shape<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># \u8f93\u51fa&#xff1a;\u9636\u6570: 1, \u5f62\u72b6: torch.Size([3])<\/span><\/p>\n<p><span class=\"token comment\"># 2 \u9636\u5f20\u91cf&#xff08;\u77e9\u9635&#xff09;<\/span><br \/>\nx2 <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">4<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">6<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">7<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u9636\u6570: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x2<span class=\"token punctuation\">.<\/span>ndim<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u5f62\u72b6: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>x2<span class=\"token punctuation\">.<\/span>size<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># \u8f93\u51fa&#xff1a;\u9636\u6570: 2, \u5f62\u72b6: torch.Size([2, 3])<\/span><\/p>\n<h4>1.3 \u5f20\u91cf\u7684\u5173\u952e\u5c5e\u6027<\/h4>\n<table>\n<tr>\u5c5e\u6027\u8bf4\u660e\u793a\u4f8b<\/tr>\n<tbody>\n<tr>\n<td align=\"left\">shape \/ size()<\/td>\n<td align=\"left\">\u5f20\u91cf\u5f62\u72b6<\/td>\n<td align=\"left\">torch.Size([2, 3])<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">ndim \/ dim()<\/td>\n<td align=\"left\">\u7ef4\u5ea6\u6570\u91cf<\/td>\n<td align=\"left\">2<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">dtype<\/td>\n<td align=\"left\">\u6570\u636e\u7c7b\u578b<\/td>\n<td align=\"left\">torch.float32<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">numel()<\/td>\n<td align=\"left\">\u5143\u7d20\u603b\u6570<\/td>\n<td align=\"left\">6<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">device<\/td>\n<td align=\"left\">\u5b58\u50a8\u8bbe\u5907<\/td>\n<td align=\"left\">cpu \/ cuda:0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>\u4e8c\u3001\u5f20\u91cf\u7684\u521b\u5efa\u65b9\u5f0f<\/h3>\n<h4>2.1 \u4ece\u6570\u636e\u521b\u5efa<\/h4>\n<p><span class=\"token comment\"># \u6839\u636e\u6307\u5b9a\u6570\u636e\u521b\u5efa\u5f20\u91cf<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6307\u5b9a\u6570\u636e\u7c7b\u578b<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> dtype<span class=\"token operator\">&#061;<\/span>torch<span class=\"token punctuation\">.<\/span>float32<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>dtype<span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># torch.float32<\/span><\/p>\n<h4>2.2 \u6839\u636e\u5f62\u72b6\u521b\u5efa&#xff08;\u968f\u673a\u521d\u59cb\u5316&#xff09;<\/h4>\n<p><span class=\"token comment\"># \u521b\u5efa 2 \u884c 3 \u5217\u7684\u6d6e\u70b9\u5f20\u91cf&#xff0c;\u9ed8\u8ba4 float32<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>Tensor<span class=\"token punctuation\">(<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6ce8\u610f&#xff1a;Tensor \u5927\u5199\u7528\u4e8e\u521b\u5efa\u7a7a\u5f20\u91cf<\/span><br \/>\n<span class=\"token comment\"># tensor \u5c0f\u5199\u7528\u4e8e\u4ece\u6570\u636e\u521b\u5efa<\/span><\/p>\n<h4>2.3 \u521b\u5efa\u6307\u5b9a\u7c7b\u578b\u7684\u5f20\u91cf<\/h4>\n<p><span class=\"token comment\"># \u5404\u7c7b\u5f20\u91cf\u521b\u5efa\u65b9\u5f0f<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>IntTensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>      <span class=\"token comment\"># int32<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>LongTensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>     <span class=\"token comment\"># int64<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>FloatTensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2.5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># float32&#xff08;\u9ed8\u8ba4&#xff09;<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>DoubleTensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>   <span class=\"token comment\"># float64<\/span><\/p>\n<p><span class=\"token comment\"># \u4e0d\u663e\u793a\u7684\u7c7b\u578b&#xff1a;FloatTensor\u2192float32&#xff0c;LongTensor\u2192int64<\/span><\/p>\n<h4>2.4 \u7ebf\u6027\u5f20\u91cf<\/h4>\n<p><span class=\"token comment\"># \u56fa\u5b9a\u6b65\u957f\u751f\u6210 [start, end, step)&#xff0c;\u5de6\u95ed\u53f3\u5f00<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>arange<span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># tensor([0, 2, 4, 6, 8])<\/span><\/p>\n<p><span class=\"token comment\"># \u56fa\u5b9a\u5143\u7d20\u6570\u751f\u6210 [start, end]&#xff0c;\u5de6\u95ed\u53f3\u95ed\u7684\u7b49\u5dee\u6570\u5217<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>linspace<span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">9<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># tensor([0., 1., 2., &#8230;, 9.])<\/span><\/p>\n<h4>2.5 \u968f\u673a\u5f20\u91cf \u2b50\u2b50\u2b50<\/h4>\n<p><span class=\"token comment\"># \u6807\u51c6\u6b63\u6001\u5206\u5e03\u968f\u673a\u6570<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>randn<span class=\"token punctuation\">(<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u968f\u673a\u6574\u6570 [low, high)&#xff0c;\u5de6\u95ed\u53f3\u5f00<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>randint<span class=\"token punctuation\">(<\/span>low<span class=\"token operator\">&#061;<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> high<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">,<\/span> size<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">4<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">6<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u8bbe\u7f6e\u968f\u673a\u79cd\u5b50&#xff0c;\u4fdd\u8bc1\u53ef\u590d\u73b0<\/span><br \/>\ntorch<span class=\"token punctuation\">.<\/span>manual_seed<span class=\"token punctuation\">(<\/span><span class=\"token number\">100<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>randn<span class=\"token punctuation\">(<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;\u968f\u673a\u6570\u79cd\u5b50:&#039;<\/span><span class=\"token punctuation\">,<\/span> torch<span class=\"token punctuation\">.<\/span>initial_seed<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>2.6 \u521b\u5efa\u5168 0 \/ \u5168 1 \/ \u5168\u6307\u5b9a\u503c\u5f20\u91cf<\/h4>\n<p><span class=\"token comment\"># \u5168 0 \u5f20\u91cf<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>zeros<span class=\"token punctuation\">(<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6839\u636e\u5f62\u72b6\u521b\u5efa\u5168 0&#xff08;\u590d\u5236\u8f93\u5165\u5f20\u91cf\u7684\u5f62\u72b6&#xff09;<\/span><br \/>\nbase <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>zeros_like<span class=\"token punctuation\">(<\/span>base<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u5168 1 \u5f20\u91cf<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>ones<span class=\"token punctuation\">(<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>ones_like<span class=\"token punctuation\">(<\/span>base<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u5168\u6307\u5b9a\u503c<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>full<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span>      <span class=\"token comment\"># \u5168 10<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>full_like<span class=\"token punctuation\">(<\/span>base<span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># \u6839\u636e base \u7684\u5f62\u72b6&#xff0c;\u5168 20<\/span><\/p>\n<p>\u6613\u9519\u70b9&#xff1a;<\/p>\n<ul>\n<li>torch.zeros(3) \u2192 \u9ed8\u8ba4 float32<\/li>\n<li>torch.zeros_like(\u6570\u636e) \u2192 \u7c7b\u578b\u8ddf\u7740\u8f93\u5165\u8d70<\/li>\n<\/ul>\n<hr \/>\n<h3>\u4e09\u3001\u5f20\u91cf\u6570\u636e\u7c7b\u578b\u8f6c\u6362<\/h3>\n<h4>3.1 \u5f20\u91cf\u4e0e NumPy \u4e92\u8f6c<\/h4>\n<p><span class=\"token keyword\">import<\/span> numpy <span class=\"token keyword\">as<\/span> np<br \/>\n<span class=\"token keyword\">import<\/span> torch<\/p>\n<p><span class=\"token comment\"># &#061;&#061;&#061; \u5f20\u91cf \u2192 NumPy&#xff08;\u5171\u4eab\u5185\u5b58&#xff01;&#xff09;&#061;&#061;&#061;<\/span><br \/>\ndata_tensor <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">4<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndata_numpy <span class=\"token operator\">&#061;<\/span> data_tensor<span class=\"token punctuation\">.<\/span>numpy<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u26a0\ufe0f \u5171\u4eab\u5185\u5b58&#xff1a;\u4fee\u6539\u4e00\u4e2a&#xff0c;\u53e6\u4e00\u4e2a\u4e5f\u53d8<\/span><br \/>\ndata_numpy<span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">100<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data_tensor<span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># tensor([100, 3, 4])<\/span><\/p>\n<p><span class=\"token comment\"># \u4f7f\u7528 copy \u907f\u514d\u5171\u4eab<\/span><br \/>\ndata_numpy <span class=\"token operator\">&#061;<\/span> data_tensor<span class=\"token punctuation\">.<\/span>numpy<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>copy<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># &#061;&#061;&#061; NumPy \u2192 \u5f20\u91cf &#061;&#061;&#061;<\/span><br \/>\ndata_numpy <span class=\"token operator\">&#061;<\/span> np<span class=\"token punctuation\">.<\/span>array<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">4<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u65b9\u5f0f 1&#xff1a;\u5171\u4eab\u5185\u5b58<\/span><br \/>\ndata_tensor <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>from_numpy<span class=\"token punctuation\">(<\/span>data_numpy<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u65b9\u5f0f 2&#xff1a;\u4e0d\u5171\u4eab\u5185\u5b58&#xff08;\u63a8\u8350&#xff09;<\/span><br \/>\ndata_tensor <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span>data_numpy<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># \u6216<\/span><br \/>\ndata_tensor <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>from_numpy<span class=\"token punctuation\">(<\/span>data_numpy<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>clone<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>3.2 \u63d0\u53d6\u6807\u91cf\u503c<\/h4>\n<p><span class=\"token comment\"># \u53ea\u6709\u5355\u5143\u7d20\u5f20\u91cf\u624d\u80fd\u7528 item()<\/span><br \/>\nx <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">.<\/span>item<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># 2<\/span><\/p>\n<p>x <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>tensor<span class=\"token punctuation\">(<\/span><span class=\"token number\">22<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">.<\/span>item<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># 22<\/span><\/p>\n<p><span class=\"token comment\"># \u591a\u5143\u7d20\u5f20\u91cf\u4e0d\u80fd\u7528 item()<\/span><br \/>\nx <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>randint<span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">4<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># print(x.item())  # \u274c \u62a5\u9519&#xff01;<\/span><\/p>\n<h4>3.3 \u7c7b\u578b\u8f6c\u6362\u65b9\u6cd5<\/h4>\n<p>data <span class=\"token operator\">&#061;<\/span> torch<span class=\"token punctuation\">.<\/span>full<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>dtype<span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># torch.int64<\/span><\/p>\n<p><span class=\"token comment\"># \u65b9\u5f0f 1&#xff1a;type() \u65b9\u6cd5<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">type<\/span><span class=\"token punctuation\">(<\/span>torch<span class=\"token punctuation\">.<\/span>float64<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u65b9\u5f0f 2&#xff1a;\u7b80\u6d01\u65b9\u6cd5&#xff08;\u63a8\u8350 \u2b50\u2b50\u2b50&#xff09;<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>double<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>   <span class=\"token comment\"># float64<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">float<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>    <span class=\"token comment\"># float32<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>      <span class=\"token comment\"># int32<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">long<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>     <span class=\"token comment\"># int64<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>short<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>    <span class=\"token comment\"># int16<\/span><\/p>\n<hr \/>\n<h3>\u56db\u3001\u5f20\u91cf\u57fa\u7840\u603b\u7ed3<\/h3>\n<table>\n<tr>\u64cd\u4f5c\u65b9\u6cd5\u8bf4\u660e<\/tr>\n<tbody>\n<tr>\n<td align=\"left\">\u4ece\u6570\u636e\u521b\u5efa<\/td>\n<td align=\"left\">torch.tensor(data)<\/td>\n<td align=\"left\">\u6700\u5e38\u7528<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u6309\u5f62\u72b6\u521b\u5efa<\/td>\n<td align=\"left\">torch.Tensor(m, n)<\/td>\n<td align=\"left\">\u968f\u673a\u521d\u59cb\u5316<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u6307\u5b9a\u7c7b\u578b\u521b\u5efa<\/td>\n<td align=\"left\">torch.FloatTensor() \u7b49<\/td>\n<td align=\"left\">\u660e\u786e\u6570\u636e\u7c7b\u578b<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u7ebf\u6027\u5e8f\u5217<\/td>\n<td align=\"left\">torch.arange() \/ linspace()<\/td>\n<td align=\"left\">\u7b49\u5dee\u6570\u5217<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u968f\u673a\u5f20\u91cf<\/td>\n<td align=\"left\">torch.randn() \/ randint()<\/td>\n<td align=\"left\">\u6b63\u6001\/\u5747\u5300\u5206\u5e03<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u5168\u503c\u5f20\u91cf<\/td>\n<td align=\"left\">torch.zeros() \/ ones() \/ full()<\/td>\n<td align=\"left\">0\/1\/\u6307\u5b9a\u503c<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u8f6c NumPy<\/td>\n<td align=\"left\">.numpy()<\/td>\n<td align=\"left\">\u5171\u4eab\u5185\u5b58<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u4ece NumPy \u8f6c<\/td>\n<td align=\"left\">torch.from_numpy() \/ torch.tensor()<\/td>\n<td align=\"left\">\u540e\u8005\u4e0d\u5171\u4eab<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u7c7b\u578b\u8f6c\u6362<\/td>\n<td align=\"left\">.float() \/ .double() \/ .int()<\/td>\n<td align=\"left\">\u7b80\u6d01\u63a8\u8350<\/td>\n<\/tr>\n<tr>\n<td align=\"left\">\u53d6\u6807\u91cf\u503c<\/td>\n<td align=\"left\">.item()<\/td>\n<td align=\"left\">\u4ec5\u5355\u5143\u7d20\u53ef\u7528<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>\u4e94\u3001\u4e0b\u4e00\u7bc7\u9884\u544a<\/h3>\n<p>PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0&#xff08;\u56db&#xff09;&#xff1a;\u5f20\u91cf\u8fd0\u7b97\u4e0e\u53d8\u5f62\u2014\u2014\u6570\u503c\u8ba1\u7b97\u4e0e\u7d22\u5f15\u8fdb\u9636<\/p>\n<p>\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5f20\u91cf\u7684\u70b9\u4e58\u3001\u77e9\u9635\u4e58\u6cd5\u3001\u7edf\u8ba1\u51fd\u6570\u3001\u7d22\u5f15\u64cd\u4f5c&#xff08;\u5e03\u5c14\u7d22\u5f15\u3001\u591a\u7ef4\u7d22\u5f15&#xff09;&#xff0c;\u4ee5\u53ca reshape\u3001transpose\u3001view \u7b49\u5f62\u72b6\u53d8\u6362\u64cd\u4f5c\u3002<\/p>\n<hr \/>\n<p>\u5982\u679c\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u5e2e\u52a9&#xff0c;\u6b22\u8fce\u70b9\u8d5e\u3001\u6536\u85cf\u3001\u5173\u6ce8&#xff01;\u4f60\u7684\u652f\u6301\u662f\u6211\u6301\u7eed\u521b\u4f5c\u7684\u52a8\u529b\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7cfb\u5217\u5bfc\u8bfb&#xff1a;\u672c\u7cfb\u5217\u5171 6 \u7bc7&#xff0c;\u4ece PyTorch \u6846\u67b6\u5165\u95e8\u5230\u5b9e\u6218\u6848\u4f8b&#xff0c;\u5e26\u4f60\u7cfb\u7edf\u638c\u63e1\u6df1\u5ea6\u5b66\u4e60\u5f00\u53d1\u3002\u4e0a\u4e00\u7bc7&#xff1a;PyTorch \u4f18\u52bf\u5168\u89e3\u6790\u2014\u2014\u4e3a\u4ec0\u4e48\u79d1\u7814\u548c\u5de5\u4e1a\u90fd\u7231\u5b83 \u4e00\u3001\u4ec0\u4e48\u662f\u5f20\u91cf&#xff08;Tensor&#xff09;<br \/>\n1.1 \u5f20\u91cf\u662f PyTorch \u7684\u6838\u5fc3<br \/>\n\u5f20\u91cf\u662f PyTorch \u4e2d\u6700\u6838\u5fc3\u7684\u6570\u636e\u62bd\u8c61&#xff0c;\u53ef\u4ee5\u7406\u89e3\u4e3a&#xff1a;<br \/>\n\u5143\u7d20\u4e3a\u540c\u4e00\u79cd\u6570\u636e\u7c7b\u578b\u7684\u591a\u7ef4\u77e9\u9635\u4e0e NumPy \u6570\u7ec4\u7c7b\u4f3c&#xff0c;\u4f46\u652f\u6301<\/p>\n","protected":false},"author":2,"featured_media":88200,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[9099,152,86,305],"topic":[],"class_list":["post-88201","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-9099","tag-pytorch","tag-86","tag-305"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/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.wsisp.com\/helps\/88201.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u7cfb\u5217\u5bfc\u8bfb&#xff1a;\u672c\u7cfb\u5217\u5171 6 \u7bc7&#xff0c;\u4ece PyTorch \u6846\u67b6\u5165\u95e8\u5230\u5b9e\u6218\u6848\u4f8b&#xff0c;\u5e26\u4f60\u7cfb\u7edf\u638c\u63e1\u6df1\u5ea6\u5b66\u4e60\u5f00\u53d1\u3002\u4e0a\u4e00\u7bc7&#xff1a;PyTorch \u4f18\u52bf\u5168\u89e3\u6790\u2014\u2014\u4e3a\u4ec0\u4e48\u79d1\u7814\u548c\u5de5\u4e1a\u90fd\u7231\u5b83 \u4e00\u3001\u4ec0\u4e48\u662f\u5f20\u91cf&#xff08;Tensor&#xff09; 1.1 \u5f20\u91cf\u662f PyTorch \u7684\u6838\u5fc3 \u5f20\u91cf\u662f PyTorch \u4e2d\u6700\u6838\u5fc3\u7684\u6570\u636e\u62bd\u8c61&#xff0c;\u53ef\u4ee5\u7406\u89e3\u4e3a&#xff1a; \u5143\u7d20\u4e3a\u540c\u4e00\u79cd\u6570\u636e\u7c7b\u578b\u7684\u591a\u7ef4\u77e9\u9635\u4e0e NumPy \u6570\u7ec4\u7c7b\u4f3c&#xff0c;\u4f46\u652f\u6301\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/88201.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-07-31T09:32:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/07\/20260731093243-6a6c6bbb61a07.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/88201.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/88201.html\",\"name\":\"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-07-31T09:32:45+00:00\",\"dateModified\":\"2026-07-31T09:32:45+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/88201.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/88201.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/88201.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","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.wsisp.com\/helps\/88201.html","og_locale":"zh_CN","og_type":"article","og_title":"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u7cfb\u5217\u5bfc\u8bfb&#xff1a;\u672c\u7cfb\u5217\u5171 6 \u7bc7&#xff0c;\u4ece PyTorch \u6846\u67b6\u5165\u95e8\u5230\u5b9e\u6218\u6848\u4f8b&#xff0c;\u5e26\u4f60\u7cfb\u7edf\u638c\u63e1\u6df1\u5ea6\u5b66\u4e60\u5f00\u53d1\u3002\u4e0a\u4e00\u7bc7&#xff1a;PyTorch \u4f18\u52bf\u5168\u89e3\u6790\u2014\u2014\u4e3a\u4ec0\u4e48\u79d1\u7814\u548c\u5de5\u4e1a\u90fd\u7231\u5b83 \u4e00\u3001\u4ec0\u4e48\u662f\u5f20\u91cf&#xff08;Tensor&#xff09; 1.1 \u5f20\u91cf\u662f PyTorch \u7684\u6838\u5fc3 \u5f20\u91cf\u662f PyTorch \u4e2d\u6700\u6838\u5fc3\u7684\u6570\u636e\u62bd\u8c61&#xff0c;\u53ef\u4ee5\u7406\u89e3\u4e3a&#xff1a; \u5143\u7d20\u4e3a\u540c\u4e00\u79cd\u6570\u636e\u7c7b\u578b\u7684\u591a\u7ef4\u77e9\u9635\u4e0e NumPy \u6570\u7ec4\u7c7b\u4f3c&#xff0c;\u4f46\u652f\u6301","og_url":"https:\/\/www.wsisp.com\/helps\/88201.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-07-31T09:32:45+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/07\/20260731093243-6a6c6bbb61a07.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/88201.html","url":"https:\/\/www.wsisp.com\/helps\/88201.html","name":"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-07-31T09:32:45+00:00","dateModified":"2026-07-31T09:32:45+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/88201.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/88201.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/88201.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"PyTorch \u6df1\u5ea6\u5b66\u4e60\u7b14\u8bb0\uff08\u4e09\uff09PyTorch \u5f20\u91cf\u57fa\u7840\u2014\u2014\u4ece\u96f6\u5f00\u59cb\u638c\u63e1 Tensor"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/88201","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=88201"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/88201\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/88200"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=88201"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=88201"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=88201"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=88201"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}