如何将tensorflow的word2vec保存在文本/二进制文件中以供以后使用kNN输出? [英] How to save the tensorflow's word2vec in text/binary file for later use of kNN output?

问题描述

我已经在tensorflow中训练了word2vec模型.但是当我保存会话时，它仅输出model.ckpt.data/.index/.meta文件.

I have trained a word2vec model in tensorflow. But when I save the session, it only outputted model.ckpt.data / .index / .meta files.

我当时正在考虑在检索最接近的单词时实施KNN方法.我看到了使用gensim的答案，但是如何将我的tensorflow word2vec模型首先保存到.txt中?

I was thinking of implementing KNN method in retrieving nearest words. I saw answers of using gensim, but how can I save my tensorflow word2vec model into .txt first?

推荐答案

我只是遇到了同样的问题，并尝试了Maxim的解决方案.

I just had the same problem and tried Maxim's solution.

您需要替换以下行:

word = word_to_idx[i]

使用

word = idx_to_word[i]

您可以使用以下代码简单地将word_to_idx-dictionary反转:

You can simply reverse the word_to_idx-dictionary with the following code:

idx_to_word = dict(zip(word_to_idx.values(), word_to_idx.keys()))

除此之外，他的解决方案效果很好.

Except for that, his solution works fine.

这篇关于如何将tensorflow的word2vec保存在文本/二进制文件中以供以后使用kNN输出?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！