{"id":1213,"date":"2024-02-01T23:04:12","date_gmt":"2024-02-01T15:04:12","guid":{"rendered":"https:\/\/www.fanyamin.com\/wordpress\/?p=1213"},"modified":"2024-02-01T23:11:34","modified_gmt":"2024-02-01T15:11:34","slug":"tensorrt-%e8%ae%ad%e7%bb%83%e5%90%8e%e6%8e%a8%e7%90%86%e7%9a%84%e5%88%a9%e5%99%a8","status":"publish","type":"post","link":"https:\/\/www.fanyamin.com\/wordpress\/?p=1213","title":{"rendered":"TensorRT \u8bad\u7ec3\u540e\u63a8\u7406\u7684\u5229\u5668"},"content":{"rendered":"<p>TensorRT is a large and flexible project. It can handle a variety of conversion and deployment workflows, and which workflow is best for you will depend on your specific use case and problem setting.<\/p>\n<p>TensorRT provides several options for deployment, but all workflows involve the conversion of your model to an optimized representation, which TensorRT refers to as an engine. <\/p>\n<p>Building a TensorRT workflow for your model involves picking the right deployment option, and the right combination of parameters for engine creation.<\/p>\n<p>refer to <a href=\"https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/quick-start-guide\/index.html\">https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/quick-start-guide\/index.html<\/a><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.fanyamin.com\/wordpress\/wp-content\/uploads\/2024\/02\/image-1706800103344.png\" alt=\"file\" \/><\/p>\n<p>TensorRT\u662f\u4e00\u4e2a\u9ad8\u6027\u80fd\u7684\u6df1\u5ea6\u5b66\u4e60\u63a8\u7406\uff08Inference\uff09\u4f18\u5316\u5668\uff0c\u53ef\u4ee5\u4e3a\u6df1\u5ea6\u5b66\u4e60\u5e94\u7528\u63d0\u4f9b\u4f4e\u5ef6\u8fdf\u3001\u9ad8\u541e\u5410\u7387\u7684\u90e8\u7f72\u63a8\u7406\u3002TensorRT\u53ef\u7528\u4e8e\u5bf9\u8d85\u5927\u89c4\u6a21\u6570\u636e\u4e2d\u5fc3\u3001\u5d4c\u5165\u5f0f\u5e73\u53f0\u6216\u81ea\u52a8\u9a7e\u9a76\u5e73\u53f0\u8fdb\u884c\u63a8\u7406\u52a0\u901f\u3002TensorRT\u73b0\u5df2\u80fd\u652f\u6301TensorFlow\u3001Caffe\u3001Mxnet\u3001Pytorch\u7b49\u51e0\u4e4e\u6240\u6709\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\uff0c\u5c06TensorRT\u548cNVIDIA\u7684GPU\u7ed3\u5408\u8d77\u6765\uff0c\u80fd\u5728\u51e0\u4e4e\u6240\u6709\u7684\u6846\u67b6\u4e2d\u8fdb\u884c\u5feb\u901f\u548c\u9ad8\u6548\u7684\u90e8\u7f72\u63a8\u7406\u3002<br \/>\nTensorRT \u662f\u4e00\u4e2aC++\u5e93\uff0c\u4ece TensorRT 3 \u5f00\u59cb\u63d0\u4f9bC++ API\u548cPython API\uff0c\u4e3b\u8981\u7528\u6765\u9488\u5bf9 NVIDIA GPU\u8fdb\u884c \u9ad8\u6027\u80fd\u63a8\u7406\uff08Inference\uff09\u52a0\u901f\u3002<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.fanyamin.com\/wordpress\/wp-content\/uploads\/2024\/02\/image-1706799124657.png\" alt=\"file\" \/><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.fanyamin.com\/wordpress\/wp-content\/uploads\/2024\/02\/image-1706798478654.png\" alt=\"file\" \/><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.fanyamin.com\/wordpress\/wp-content\/uploads\/2024\/02\/image-1706800264668.png\" alt=\"file\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>TensorRT is a large and flexible project. It can handle a variety of conversion and deployment workflows, and which workflow is best for you will depend on your specific use case and problem setting. TensorRT provides several options for deployment, but all workflows involve the conversion of your model to an optimized representation, which TensorRT [&hellip;] <a class=\"read-more\" href=\"https:\/\/www.fanyamin.com\/wordpress\/?p=1213\" title=\"Permanent Link to: TensorRT \u8bad\u7ec3\u540e\u63a8\u7406\u7684\u5229\u5668\">&rarr;Read&nbsp;more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-1213","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1213"}],"collection":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1213"}],"version-history":[{"count":5,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1213\/revisions"}],"predecessor-version":[{"id":1222,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1213\/revisions\/1222"}],"wp:attachment":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}