{"description":"This article is a translation of Japanese ver. \u65e5\u672c\u8a9e\u7248\u306f\u3053\u3061\u3089*1 Hi, this is chang. Today, I tried to accelerate inference. I published defection viewer not long ago*2*3. Its inference took about 6 sec. I investigated why it took so long and discovered that the time was costed in running a session of Tenso\u2026","categories":["Deep learning"],"provider_url":"https://hatena.blog","type":"rich","width":"100%","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fchanglikesdesktop.hatenablog.com%2Fentry%2F2020%2F09%2F08%2F045101\" title=\"Accelerate inference by running tensorflow&#39;s session in advance   - \u30aa\u30c3\u30b5\u30f3\u306fDesktop\u304c\u597d\u304d\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","version":"1.0","provider_name":"Hatena Blog","url":"https://changlikesdesktop.hatenablog.com/entry/2020/09/08/045101","blog_title":"\u30aa\u30c3\u30b5\u30f3\u306fDesktop\u304c\u597d\u304d","blog_url":"https://changlikesdesktop.hatenablog.com/","author_url":"https://blog.hatena.ne.jp/changlikesdesktop/","author_name":"changlikesdesktop","published":"2020-09-08 04:51:01","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/c/changlikesdesktop/20200901/20200901054543.png","height":"190","title":"Accelerate inference by running tensorflow's session in advance  "}