{"height":"190","published":"2017-03-04 00:00:00","provider_url":"https://hatena.blog","categories":["machine learning","TensorFlow","seq2seq","RNN"],"author_url":"https://blog.hatena.ne.jp/redhornet96/","width":"100%","description":"\u524d\u56de\u3067TensorFlow\u306eseq2seq\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u82f1\u8a9e\u30d5\u30e9\u30f3\u30b9\u8a9e\u7ffb\u8a33\u3092\u5b9f\u88c5\u3057\u3066\u307f\u305f\u306e\u3067\u3059\u304c\u3001\u3042\u3061\u3089\u3053\u3061\u3089\u306b\u30cf\u30de\u308a\u30dd\u30a4\u30f3\u30c8\u304c\u3042\u308a\u3001\u672a\u3060\u306b\u3046\u307e\u304f\u3044\u3063\u3066\u307e\u305b\u3093\u3002\u7d9a\u304d\u3092\u66f8\u3044\u3066\u3044\u3053\u3046\u3068\u601d\u3044\u307e\u3059\uff01 \u5b66\u7fd2\u3092\u5b9f\u884c\u3057\u305f\u3089\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30a8\u30e9\u30fc\u304c\u51fa\u3066\u3057\u307e\u3063\u305f\u306e\u3067\u3053\u308c\u306e\u5bfe\u51e6\u304b\u3089\u3002 $ python translate.py --data_dir data --train_dir train \u7565... ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[64,40,1,1024] [[No\u2026","author_name":"redhornet96","provider_name":"Hatena Blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fwww.mof-mof.co.jp%2Ftech-blog%2Ftensorflow-seq2seq-2\" title=\" TensorFlow\u306eseq2seq\u3067\u82f1\u4ecf\u8a9e\u7ffb\u8a33\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u8a66\u3059\u2461 - \u3082\u3075\u3082\u3075\u6280\u8853\u90e8\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","url":"https://www.mof-mof.co.jp/tech-blog/tensorflow-seq2seq-2","type":"rich","title":" TensorFlow\u306eseq2seq\u3067\u82f1\u4ecf\u8a9e\u7ffb\u8a33\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u8a66\u3059\u2461","image_url":null,"blog_url":"https://www.mof-mof.co.jp/tech-blog/","blog_title":"\u3082\u3075\u3082\u3075\u6280\u8853\u90e8","version":"1.0"}