Keras入门

本文的主线 环境 => 示例

环境

• 安装Anaconda => 重启终端

conda create --name ai-abc python=3.7

conda activate ai-abc

python -V
# Python 3.7.11

conda install tensorflow

python

import tensorflow as tf
from tensorflow import keras

print(tf.__version__)
# 2.0.0
print(keras.__version__)
# 2.2.4-tf

示例

vim hello-keras.py

from tensorflow import keras
import matplotlib.pyplot as plt

# 下载数据
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels)))
print(len(train_data[0]), len(train_data[1]))

# 准备数据
word_index = imdb.get_word_index()
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
print(' '.join([reverse_word_index.get(i, '?') for i in train_data[0]]))

train_data = keras.preprocessing.sequence.pad_sequences(train_data,
                                                        value=word_index["<PAD>"],
                                                        padding='post',
                                                        maxlen=256)

test_data = keras.preprocessing.sequence.pad_sequences(test_data,
                                                       value=word_index["<PAD>"],
                                                       padding='post',
                                                       maxlen=256)
print(len(train_data[0]), len(train_data[1]))

# 构建模型
model = keras.Sequential()
model.add(keras.layers.Embedding(10000, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation='relu'))
model.add(keras.layers.Dense(1, activation='sigmoid'))
model.summary()
model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

# 训练模型
x_val = train_data[:10000]
partial_x_train = train_data[10000:]

y_val = train_labels[:10000]
partial_y_train = train_labels[10000:]

history = model.fit(partial_x_train,
                    partial_y_train,
                    epochs=20,
                    batch_size=512,
                    validation_data=(x_val, y_val),
                    verbose=1)

# 评估模型
results = model.evaluate(test_data, test_labels, verbose=2)
print(results)

# 绘制图表
history_dict = history.history
acc = history_dict['accuracy']
val_acc = history_dict['val_accuracy']
loss = history_dict['loss']
val_loss = history_dict['val_loss']

epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

conda install matplotlib

python hello-keras.py

keras-introduction-01.png

参考

• Install TensorFlow

• Keras vs. tf.keras: What’s the difference in TensorFlow 2.0?

• 电影评论文本分类