gensim Word2vec转移学习(来自非gensim模型)

问题描述

我有一组经过神经网络训练的嵌入，与gensim的word2vec无关.

I have a set of embeddings trained with a neural network that has nothing to do with gensim's word2vec.

我想将这些嵌入用作gensim.Word2vec中的初始权重.

I want to use these embeddings as the initial weights in gensim.Word2vec.

现在我看到的是我可以model.load(SOME_MODEL)，然后继续训练，但这需要使用gensim模型作为输入.另外reset_from()似乎只接受其他gensim模型.但是就我而言，我没有一个gensim模型，而是一个word2vec嵌入格式的文本文件.

Now what I did see is that I can model.load(SOME_MODEL) and then continue training, but it requires a gensim modle as input. Also reset_from() seems to only accept other gensim model.But in my case, I don't have a gensim model to start from, but a text file in word2vec format of embeddings.

那么我如何开始将学习内容从word2vec文本文件传输到gensim.Word2vec?

So how do I start transfer learning from an word2vec text file to gensim.Word2vec?

推荐答案

您可以使用原始Word2Vec模型的键向量格式加载其他模型

You can load other models using the key vector format of the original Word2Vec model

import io

from gensim.models.keyedvectors import KeyedVectors

# first line is vocab size and vector dim
model_buf = io.StringIO("""
2 3
word0 -0.000737 -0.002106 0.001851
word1 -0.000878 -0.002106 0.002834
""".lstrip())

model = KeyedVectors.load_word2vec_format(model_buf, binary=False)

model['word0']

这篇关于gensim Word2vec转移学习(来自非gensim模型)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！