自然语言处理--使用 TensorBoard 可视化词嵌入

TensorBoard 是一个可视化词嵌入的好工具。特别是当训练自己的、基于特定领域的词嵌入时，嵌入可视化可以帮助验证语义相似性。将词模型转换为 TensorBoard 可以处理的格式很简单。将词向量和向量标签加载到 TensorBoard 后，它将执行降维到二维或三维的操作。TensorBoard目前提供 3 种降维方法：PCA、t-SNE 和自定义降维。

代码展示了如何将词嵌入转换为 TensorBoard 格式并生成投影数据：

import os
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as np
from io import open
from tensorboard.plugins import projector

# Tensorboard的PROJECTOR有着很美好的功能，它能够帮助我们查看网络中数据在二维、三维下的效果
# create_projection 函数有 3 个参数：嵌入数据、投影的名称，以及存储投影文件的路径
def create_projection(projection_data, projection_name='tensorboard_viz',
                        path='xxx\\tmp\\'):
    # 数据
    meta_file = "{}.tsv".format(projection_name)
    vector_dim = len(projection_data[0][1])
    samples = len(projection_data)
    projection_matrix = np.zeros((samples, vector_dim))
    with open(os.path.join(path, meta_file), 'w') as file_metadata:
        for i, row in enumerate(projection_data):
            label, vector = row[0], row[1]
            projection_matrix[i] = np.array(vector)
            file_metadata.write("{}\n".format(label))

    # 要创建 TensorBoard 投影，需要创建一个TensorFlow 会话
    sess = tf.InteractiveSession()
    # Tensorboard中显示的PROJECTOR数据是从saver()保存的张量数据中取出，
    # 所以在Embedding机制中通过一个tf.Variable变量(即下面的embedding_var)来存储需要投影的图像或者数据
    embedding = tf.Variable(projection_matrix, trainable=False, name=projection_name)
    tf.global_variables_initializer().run()

    saver = tf.train.Saver()
    writer = tf.summary.FileWriter(path, sess.graph)

    # 注册一个Projector，这样Tensorboard才显示Projector，而注册Projector则需要Embedding的信息，
    # 比如嵌入的变量名、tsv文件路径(下有解释)、sprite图像路径(下有解释)等
    config = projector.ProjectorConfig()
    embed = config.embeddings.add()
    embed.tensor_name = '{}'.format(projection_name)
    # Specify where you find the metadata
    embed.metadata_path = os.path.join(path, meta_file)
    # visualize_embeddings 方法将投影结果写入路径中，然后就可以使用 TensorBoard 了
    projector.visualize_embeddings(writer, config)

    saver.save(sess, os.path.join(path, '{}.ckpt'.format(projection_name)))
    print('Run `tensorboard --logdir={0}` to run visualize result on tensorboard'.format(path))

projection_name = "NLP_in_Action"
# 示例数据
projection_data = [
                    ('car1', [0.34, 0.21, -0.72, 0.54, 0.58, 0.87, 0.98]),
                    ('car2', [0.44, 0.61, -3.72, 3.54, 0.98, 0.57, 0.28]),
                    ('car3', [1.34, 1.21, -0.72, 0.54, 4.58, 0.87, 0.98]),
                    ('car4', [0.94, 0.21, -5.72, 0.54, 3.58, 0.17, 0.48]),
                    ('car5', [3.34, 0.21, -5.72, 0.54, 0.5, 0.87, 4.98])]
create_projection(projection_data, projection_name)