使用一层LSTM与两层LSTM比较

使用一层对应的LSTM

from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow_datasets as tfds
import tensorflow as tf

# Get the data
dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True, as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']
tokenizer = info.features['text'].encoder

BUFFER_SIZE = 10000
BATCH_SIZE = 64
train_dataset = train_dataset.shuffle(BUFFER_SIZE)
train_dataset = train_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(train_dataset))
test_dataset = test_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(test_dataset))

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(tokenizer.vocab_size, 64),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.summary()
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

NUM_EPOCHS = 10
history = model.fit(train_dataset, epochs=NUM_EPOCHS, validation_data=test_dataset)
import matplotlib.pyplot as plt
def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()
plot_graphs(history, 'accuracy')
plot_graphs(history, 'loss')

对应的层数关系如下：

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
embedding (Embedding)        (None, None, 64)          523840
_________________________________________________________________
bidirectional (Bidirectional (None, 128)               66048
_________________________________________________________________
dense (Dense)                (None, 64)                8256
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 65
=================================================================

使用多层的LSTM将中间的神经网络代码修改一下：

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(tokenizer.vocab_size, 64),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64, return_sequences=True)),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

对应的结构如下：

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
embedding (Embedding)        (None, None, 64)          523840
_________________________________________________________________
bidirectional (Bidirectional (None, None, 128)         66048
_________________________________________________________________
bidirectional_1 (Bidirection (None, 64)                41216
_________________________________________________________________
dense (Dense)                (None, 64)                4160
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 65
=================================================================

一层的LSTM与多层的LSTM准确率图片进行比较
一层的LSTM与多层的LSTM损失率进行比较
可以看出一层的LSTM与多层的LSTM的区别，一层的LSTM中间有一段锯齿状的图像，
如果将迭代的次数增加到50次的时候：
我们的一层LSTM在提高准确率的时候也容易出现骤降，最终结果可能很好，但是这些骤降使我们对结果产生怀疑，第二章图片的曲线更加光滑，使我们对其结果更有信心。另外注意最终的准确率稳定在80%左右。
损失函数迭代图有同样的变化