IMDB数据集使用tensorflow训练优化过程

下面是tf官网的例子，https://www.tensorflow.org/tutorials/keras/overfit_and_underfit?hl=zh-cn

# coding: utf-8

# In[1]:

import tensorflow as tf
from tensorflow import keras

import numpy as np
import matplotlib.pyplot as plt

print(tf.__version__)


# In[3]:

NUM_WORDS = 10000
(train_data, train_labels), (test_data, test_labels) = keras.datasets.imdb.load_data(num_words=NUM_WORDS)


# In[4]:

def multi_hot_sequences(sequences, dimension):
    # Create an all-zero matrix of shape (len(sequences), dimension)
    results = np.zeros((len(sequences), dimension))
    for i, word_indices in enumerate(sequences):
        results[i, word_indices] = 1.0  # set specific indices of results[i] to 1s
    return results

train_data = multi_hot_sequences(train_data, dimension=NUM_WORDS)
test_data = multi_hot_sequences(test_data, dimension=NUM_WORDS)


# In[6]:

get_ipython().magic('matplotlib inline')
plt.plot(train_data[0])


# In[7]:

#base model
baseline_model = keras.Sequential([
    # `input_shape` is only required here so that `.summary` works.
    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),
    keras.layers.Dense(16, activation=tf.nn.relu),
    keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

baseline_model.compile(optimizer='adam',
                       loss='binary_crossentropy',
                       metrics=['accuracy', 'binary_crossentropy'])

baseline_model.summary()


# In[8]:

baseline_history = baseline_model.fit(train_data,
                                      train_labels,
                                      epochs=20,
                                      batch_size=512,
                                      validation_data=(test_data, test_labels),
                                      verbose=2)


# In[9]:

smaller_model = keras.Sequential([
    keras.layers.Dense(4, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),
    keras.layers.Dense(4, activation=tf.nn.relu),
    keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

smaller_model.compile(optimizer='adam',
                loss='binary_crossentropy',
                metrics=['accuracy', 'binary_crossentropy'])

smaller_model.summary()


# In[10]:

smaller_history = smaller_model.fit(train_data,
                                    train_labels,
                                    epochs=20,
                                    batch_size=512,
                                    validation_data=(test_data, test_labels),
                                    verbose=2)


# In[11]:

bigger_model = keras.models.Sequential([
    keras.layers.Dense(512, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),
    keras.layers.Dense(512, activation=tf.nn.relu),
    keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

bigger_model.compile(optimizer='adam',
                     loss='binary_crossentropy',
                     metrics=['accuracy','binary_crossentropy'])

bigger_model.summary()


# In[12]:

bigger_history = bigger_model.fit(train_data, train_labels,
                                  epochs=20,
                                  batch_size=512,
                                  validation_data=(test_data, test_labels),
                                  verbose=2)


# In[13]:

def plot_history(histories, key='binary_crossentropy'):
  plt.figure(figsize=(16,10))

  for name, history in histories:
    val = plt.plot(history.epoch, history.history['val_'+key],
                   '--', label=name.title()+' Val')
    plt.plot(history.epoch, history.history[key], color=val[0].get_color(),
             label=name.title()+' Train')

  plt.xlabel('Epochs')
  plt.ylabel(key.replace('_',' ').title())
  plt.legend()

  plt.xlim([0,max(history.epoch)])

plot_history([('baseline', baseline_history),
              ('smaller', smaller_history),
              ('bigger', bigger_history)])


# In[14]:

l2_model = keras.models.Sequential([
    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),
                       activation=tf.nn.relu, input_shape=(NUM_WORDS,)),
    keras.layers.Dense(16, kernel_regularizer=keras.regularizers.l2(0.001),
                       activation=tf.nn.relu),
    keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

l2_model.compile(optimizer='adam',
                 loss='binary_crossentropy',
                 metrics=['accuracy', 'binary_crossentropy'])

l2_model_history = l2_model.fit(train_data, train_labels,
                                epochs=20,
                                batch_size=512,
                                validation_data=(test_data, test_labels),
                                verbose=2)


# In[15]:

plot_history([('baseline', baseline_history),
              ('l2', l2_model_history)])


# In[16]:

dpt_model = keras.models.Sequential([
    keras.layers.Dense(16, activation=tf.nn.relu, input_shape=(NUM_WORDS,)),
    keras.layers.Dropout(0.5),
    keras.layers.Dense(16, activation=tf.nn.relu),
    keras.layers.Dropout(0.5),
    keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

dpt_model.compile(optimizer='adam',
                  loss='binary_crossentropy',
                  metrics=['accuracy','binary_crossentropy'])

dpt_model_history = dpt_model.fit(train_data, train_labels,
                                  epochs=20,
                                  batch_size=512,
                                  validation_data=(test_data, test_labels),
                                  verbose=2)


# In[17]:

plot_history([('baseline', baseline_history),
              ('dropout', dpt_model_history)])

下面总结一下防止神经网络出现过拟合的最常见方法：

获取更多训练数据。
降低网络容量。
添加权重正则化。
添加丢弃层。
还有两个重要的方法在本指南中没有介绍：数据增强和批次归一化。