[Keras深度学习浅尝]实战四· Embedding实现 IMDB数据集影评文本分类
此实战来源于TensorFlow Keras官方教程
先更新代码在这里，后面找时间理解注释一下。
# TensorFlow and tf.keras
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
import tensorflow as tf
from tensorflow import keras
# Helper libraries
import numpy as np
import matplotlib.pyplot as plt
print(tf.__version__)
1.12.0
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17465344/17464789 [==============================] - 12s 1us/step
print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels)))
Training entries: 25000, labels: 25000
print(train_data[0])
len(train_data[0]), len(train_data[1])
[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]
(218, 189)
# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()
# The first indices are reserved
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()])
def decode_review(text):
return ' '.join([reverse_word_index.get(i, '?') for i in text])
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb_word_index.json
1646592/1641221 [==============================] - 2s 1us/step
decode_review(train_data[0])
"<START> this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert <UNK> is an amazing actor and now the same being director <UNK> father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for <UNK> and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also <UNK> to the two little boy's that played the <UNK> of norman and paul they were just brilliant children are often left out of the <UNK> list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all"
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)
len(train_data[0]), len(train_data[1])
(256, 256)
print(train_data[0])
[ 1 14 22 16 43 530 973 1622 1385 65 458 4468 66 3941
4 173 36 256 5 25 100 43 838 112 50 670 2 9
35 480 284 5 150 4 172 112 167 2 336 385 39 4
172 4536 1111 17 546 38 13 447 4 192 50 16 6 147
2025 19 14 22 4 1920 4613 469 4 22 71 87 12 16
43 530 38 76 15 13 1247 4 22 17 515 17 12 16
626 18 2 5 62 386 12 8 316 8 106 5 4 2223
5244 16 480 66 3785 33 4 130 12 16 38 619 5 25
124 51 36 135 48 25 1415 33 6 22 12 215 28 77
52 5 14 407 16 82 2 8 4 107 117 5952 15 256
4 2 7 3766 5 723 36 71 43 530 476 26 400 317
46 7 4 2 1029 13 104 88 4 381 15 297 98 32
2071 56 26 141 6 194 7486 18 4 226 22 21 134 476
26 480 5 144 30 5535 18 51 36 28 224 92 25 104
4 226 65 16 38 1334 88 12 16 283 5 16 4472 113
103 32 15 16 5345 19 178 32 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0]
网络模型的介绍：
1，输入网络的形状为（-1，256）
2，Embedding后为（-1，256，16）网络参数为（10000，16）
3，GlobalAveragePooling1D后为（-1，16）详细介绍见此
4，Dense1后（-1，16）网络参数为w:1616 + b:116 共计272
4，Dense2后（-1，1）网络参数为w:161 + b:11 共计17个参数
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, None, 16) 160000
_________________________________________________________________
global_average_pooling1d (Gl (None, 16) 0
_________________________________________________________________
dense (Dense) (None, 16) 272
_________________________________________________________________
dense_1 (Dense) (None, 1) 17
=================================================================
Total params: 160,289
Trainable params: 160,289
Non-trainable params: 0
_________________________________________________________________
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
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)
Train on 15000 samples, validate on 10000 samples
Epoch 1/20
15000/15000 [==============================] - 3s 215us/step - loss: 0.6919 - acc: 0.5925 - val_loss: 0.6899 - val_acc: 0.6360
Epoch 2/20
15000/15000 [==============================] - 2s 159us/step - loss: 0.6863 - acc: 0.7131 - val_loss: 0.6824 - val_acc: 0.7418
Epoch 3/20
15000/15000 [==============================] - 2s 155us/step - loss: 0.6746 - acc: 0.7652 - val_loss: 0.6676 - val_acc: 0.7583
Epoch 4/20
15000/15000 [==============================] - 2s 153us/step - loss: 0.6534 - acc: 0.7707 - val_loss: 0.6440 - val_acc: 0.7636
Epoch 5/20
15000/15000 [==============================] - 2s 153us/step - loss: 0.6221 - acc: 0.7933 - val_loss: 0.6104 - val_acc: 0.7872
Epoch 6/20
15000/15000 [==============================] - 2s 153us/step - loss: 0.5820 - acc: 0.8095 - val_loss: 0.5713 - val_acc: 0.7985
Epoch 7/20
15000/15000 [==============================] - 2s 154us/step - loss: 0.5368 - acc: 0.8271 - val_loss: 0.5297 - val_acc: 0.8163
Epoch 8/20
15000/15000 [==============================] - 2s 159us/step - loss: 0.4907 - acc: 0.8427 - val_loss: 0.4891 - val_acc: 0.8306
Epoch 9/20
15000/15000 [==============================] - 3s 170us/step - loss: 0.4478 - acc: 0.8557 - val_loss: 0.4525 - val_acc: 0.8405
Epoch 10/20
15000/15000 [==============================] - 2s 165us/step - loss: 0.4089 - acc: 0.8692 - val_loss: 0.4213 - val_acc: 0.8482
Epoch 11/20
15000/15000 [==============================] - 2s 156us/step - loss: 0.3760 - acc: 0.8791 - val_loss: 0.3977 - val_acc: 0.8541
Epoch 12/20
15000/15000 [==============================] - 2s 153us/step - loss: 0.3483 - acc: 0.8852 - val_loss: 0.3745 - val_acc: 0.8616
Epoch 13/20
15000/15000 [==============================] - 3s 171us/step - loss: 0.3236 - acc: 0.8929 - val_loss: 0.3581 - val_acc: 0.8661
Epoch 14/20
15000/15000 [==============================] - 3s 171us/step - loss: 0.3031 - acc: 0.8981 - val_loss: 0.3436 - val_acc: 0.8711
Epoch 15/20
15000/15000 [==============================] - 3s 178us/step - loss: 0.2854 - acc: 0.9033 - val_loss: 0.3322 - val_acc: 0.8732
Epoch 16/20
15000/15000 [==============================] - 3s 173us/step - loss: 0.2702 - acc: 0.9057 - val_loss: 0.3230 - val_acc: 0.8755
Epoch 17/20
15000/15000 [==============================] - 2s 165us/step - loss: 0.2557 - acc: 0.9131 - val_loss: 0.3152 - val_acc: 0.8771
Epoch 18/20
15000/15000 [==============================] - 2s 155us/step - loss: 0.2431 - acc: 0.9171 - val_loss: 0.3087 - val_acc: 0.8799
Epoch 19/20
15000/15000 [==============================] - 2s 155us/step - loss: 0.2315 - acc: 0.9213 - val_loss: 0.3033 - val_acc: 0.8812
Epoch 20/20
15000/15000 [==============================] - 2s 164us/step - loss: 0.2213 - acc: 0.9236 - val_loss: 0.2991 - val_acc: 0.8821
results = model.evaluate(test_data, test_labels)
print(results)
25000/25000 [==============================] - 1s 38us/step
[0.3124048164367676, 0.87232]
history_dict = history.history
history_dict.keys()
dict_keys(['val_loss', 'val_acc', 'loss', 'acc'])
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
plt.clf() # clear figure
acc_values = history_dict['acc']
val_acc_values = history_dict['val_acc']
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()
