{"title":"Chainer\u306ecuDNN-RNN(NStepLSTM)\u306e\u3068\u3063\u304b\u304b\u308a","image_url":null,"width":"100%","blog_url":"https://studylog.hateblo.jp/","provider_name":"Hatena Blog","blog_title":"studylog/\u5317\u306e\u96f2","type":"rich","url":"https://studylog.hateblo.jp/entry/2016/10/03/095406","version":"1.0","author_url":"https://blog.hatena.ne.jp/kitanokumo/","provider_url":"https://hatena.blog","author_name":"kitanokumo","categories":["chainer"],"published":"2016-10-03 09:54:06","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fstudylog.hateblo.jp%2Fentry%2F2016%2F10%2F03%2F095406\" title=\"Chainer\u306ecuDNN-RNN(NStepLSTM)\u306e\u3068\u3063\u304b\u304b\u308a - studylog/\u5317\u306e\u96f2\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","description":"16.0\u306e\u65b0\u6a5f\u80fdNstepLSTM\u306fcuDNN5.0\u4ee5\u964d\u3067\u6700\u9069\u5316\u3055\u308c\u305fcuDNN-RNN\u3092\u5229\u7528\u3067\u304d\u307e\u3059\u3002\u901f\u304f\u306a\u308b\u3089\u3057\u3044\u3067\u3059\u3002 Optimizing Recurrent Neural Networks in cuDNN 5 | Parallel Forall\u3053\u308c\u306e\u826f\u3044\u6240\u306f\u6b21\u5143\u6570\u304c\u5408\u308f\u306a\u3044\u30c7\u30fc\u30bf\u3067\u3082\u30df\u30cb\u30d0\u30c3\u30c1\u51e6\u7406\u304c\u7c21\u5358\u306b\u3067\u304d\u308b\u70b9\u3067\u3059\u3002 \u518d\u63b2\u3057\u307e\u3059\u304c\u4ee5\u524d\u306f\u3053\u3093\u306a\u98a8\u306b\u3084\u3063\u3066\u3044\u307e\u3057\u305f\u3002 \u53ef\u5909\u9577\u30c7\u30fc\u30bf\u306e\u30df\u30cb\u30d0\u30c3\u30c1\u3092chainer\u306ewhere\u3067\u3084\u308b - studylog/\u5317\u306e\u96f2 \u4ee5\u524d\u306e\u3084\u308a\u65b9 \u624b\u98061(\u6b21\u5143\u304c\u5408\u3063\u3066\u306a\u3044) \u30c7\u30fc\u30bfA 1 2 \u30c7\u30fc\u30bfB 1 2 3\u624b\u98062(0\u3067\u672b\u5c3e\u3092\u57cb\u3081\u3066\u6b21\u5143\u3092\u5408\u308f\u305b\u308b) \u30c7\u30fc\u30bfA\u2026","height":"190"}