[英]How to use pretrained Word2Vec model in Tensorflow
I have a Word2Vec
model which is trained in Gensim
. 我有一个
Word2Vec
模型,在Gensim
训练。 How can I use it in Tensorflow
for Word Embeddings
. 如何在
Tensorflow
使用它进行Word Embeddings
。 I don't want to train Embeddings from scratch in Tensorflow. 我不想在Tensorflow中从头开始训练嵌入。 Can someone tell me how to do it with some example code?
有人可以告诉我如何使用一些示例代码吗?
Let's assume you have a dictionary and inverse_dict list, with index in list corresponding to most common words: 假设你有一个字典和inverse_dict列表,列表中的索引对应于最常见的单词:
vocab = {'hello': 0, 'world': 2, 'neural':1, 'networks':3}
inv_dict = ['hello', 'neural', 'world', 'networks']
Notice how the inverse_dict index corresponds to the dictionary values. 注意inverse_dict索引如何对应于字典值。 Now declare your embedding matrix and get the values:
现在声明你的嵌入矩阵并获取值:
vocab_size = len(inv_dict)
emb_size = 300 # or whatever the size of your embeddings
embeddings = np.zeroes((vocab_size, emb_size))
from gensim.models.keyedvectors import KeyedVectors
model = KeyedVectors.load_word2vec_format('embeddings_file', binary=True)
for k, v in vocab.items():
embeddings[v] = model[k]
You've got your embeddings matrix. 你有嵌入矩阵。 Good.
好。 Now let's assume you want to train on the sample:
x = ['hello', 'world']
. 现在让我们假设你想训练样本:
x = ['hello', 'world']
。 But this doesn't work for our neural net. 但这对我们的神经网络不起作用。 We need to integerize:
我们需要整合:
x_train = []
for word in x:
x_train.append(vocab[word]) # integerize
x_train = np.array(x_train) # make into numpy array
Now we are good to go with embedding our samples on-the-fly 现在我们很高兴能够即时嵌入我们的样品
x_model = tf.placeholder(tf.int32, shape=[None, input_size])
with tf.device("/cpu:0"):
embedded_x = tf.nn.embedding_lookup(embeddings, x_model)
Now embedded_x
goes into your convolution or whatever. 现在
embedded_x
进入你的卷积或其他什么。 I am also assuming you are not retraining the embeddings, but simply using them. 我也假设你没有重新训练嵌入,只是简单地使用它们。 Hope that helps
希望有所帮助
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.