{"provider_name":"Hatena Blog","blog_url":"https://higepon.hatenablog.com/","image_url":null,"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhigepon.hatenablog.com%2Fentry%2F20171212%2F1513076578\" title=\"Minimum Seq2Seq implementation using Tensorflow 1.4/1.5 API - higepon blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_title":"higepon blog","height":"190","title":"Minimum Seq2Seq implementation using Tensorflow 1.4/1.5 API","categories":[],"version":"1.0","description":"This is minimum Seq2Seq implementation using Tensorflow 1.4/1.5 API with some comments, which supports Attention and Beam Search and is based on tensorflow/nmt/README.md. I'd recommend you run this in https://colab.research.google.com/.This code is also available on gist. import numpy as np import t\u2026","width":"100%","provider_url":"https://hatena.blog","author_name":"higepon","url":"https://higepon.hatenablog.com/entry/20171212/1513076578","author_url":"https://blog.hatena.ne.jp/higepon/","type":"rich","published":"2017-12-12 20:02:58"}