Gensim相当于训练步骤

问题描述 投票:1回答:1

gensim Word2Vec有一个选项,相当于TensorFlow word2vec示例中的“训练步骤”:Word2Vec Basic?如果没有,gensim使用什么默认值? gensim参数iter与训练步骤有关吗?

TensorFlow脚本包括此部分。

with tf.Session(graph=graph) as session:
    # We must initialize all variables before we use them.
    init.run()
    print('Initialized')

    average_loss = 0
    for step in xrange(num_steps):
        batch_inputs, batch_labels = generate_batch(
            batch_size, num_skips, skip_window)
        feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}

    # We perform one update step by evaluating the optimizer op (including it
    # in the list of returned values for session.run()
    _, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
    average_loss += loss_val

    if step % 2000 == 0:
        if step > 0:
            average_loss /= 2000
        # The average loss is an estimate of the loss over the last 2000 batches.
        print('Average loss at step ', step, ': ', average_loss)
        average_loss = 0

    # Note that this is expensive (~20% slowdown if computed every 500 steps)
    if step % 10000 == 0:
        sim = similarity.eval()
        for i in xrange(valid_size):
            valid_word = reverse_dictionary[valid_examples[i]]
            top_k = 8  # number of nearest neighbors
            nearest = (-sim[i, :]).argsort()[1:top_k + 1]
            log_str = 'Nearest to %s:' % valid_word
            for k in xrange(top_k):
                close_word = reverse_dictionary[nearest[k]]
                log_str = '%s %s,' % (log_str, close_word)
            print(log_str)
  final_embeddings = normalized_embeddings.eval()

在TensorFlow示例中,如果我在嵌入上执行T-SNE并使用matplotlib进行绘图,则当步数高时,该绘图看起来更合理。我正在使用1,200封电子邮件的小型语料库。一种看起来更合理的方式是将数字聚集在一起。我希望使用gensim达到相同的质量水平。

python tensorflow nlp word2vec gensim
1个回答
0
投票

是的,Word2Vec类构造函数有iter参数:

iter =语料库上的迭代次数(epochs)。默认值为5。

此外,如果直接调用Word2Vec.train()方法,则可以传入具有相同含义的epochs参数。

实际训练步骤的数量是从时期推断出来的,但取决于其他参数,如文本大小,窗口大小和批量大小。如果您只是想提高嵌入向量的质量,那么增加iter是正确的方法。

© www.soinside.com 2019 - 2024. All rights reserved.