""""
使用 Keras 和 Tensorflow Hub 对电影评论进行文本分类
"""
import numpy as np
import tensorflow as tf
# !pip install tensorflow-hub
# !pip install tfds-nightly
import tensorflow_hub as hub
import tensorflow_datasets as tfds
print("Version: ", tf.__version__)
print("Eager mode: ", tf.executing_eagerly())
print("Hub version: ", hub.__version__)
print("GPU is", "available" if tf.config.experimental.list_physical_devices("GPU") else "NOT AVAILABLE")
#这里需要保证tensorflow version >= 2.1.0
# 下载IMDB数据集
train_data, validation_data, test_data = tfds.load(
name="imdb_reviews",
split=('train[:60%]', 'train[60%:]', 'test'),
as_supervised=True)
#探索数据
# 打印前十个样本
train_examples_batch, train_labels_batch = next(iter(train_data.batch(10)))
train_examples_batch
#打印下前十个标签
train_labels_batch
#构建模型
# 创建一个使用 Tensorflow Hub 模型嵌入(embed)语句的Keras层,
# 并在几个输入样本中进行尝试。
embedding = "https://hub.tensorflow.google.cn/google/nnlm-en-dim50/2"
hub_layer = hub.KerasLayer(embedding, input_shape=[],
dtype=tf.string, trainable=True)
hub_layer(train_examples_batch[:3])
model = tf.keras.Sequential()
model.add(hub_layer)
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Dense(1))
model.summary()
# 损失函数与优化器
model.compile(optimizer='adam',
loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=['accuracy'])
# 训练模型
history = model.fit(train_data.shuffle(10000).batch(512),
epochs=10,
validation_data=validation_data.batch(512),
verbose=1)
# 评估模型
results = model.evaluate(test_data.batch(512), verbose=2)
for name, value in zip(model.metrics_names, results):
print("%s: %.3f" % (name, value))
使用 Keras 和 Tensorflow Hub 对电影评论进行文本分类
最新推荐文章于 2024-04-26 23:48:56 发布