原文：TensorFlow教程：快速入门深度学习五步法(附Keras实例)

出处：AI科技大本营(ID：rgznai100)

作者：刘子瑛

本文主要以 Keras 为例来说明像学习编程一样学习深度学习模型开发，用 5 步 + 4 种基本元素 + 9 种基本层结构，这 5-4-9 模型来总结.

通过一张图来理解下它们之间的关系：

image

1. 5-4-9

5 步法：

  1. 构造网络模型
  2. 编译模型
  3. 训练模型
  4. 评估模型
  5. 使用模型进行预测

4 种基本元素：

  1. 网络结构：由10种基本层结构和其他层结构组成
  2. 激活函数：如relu, softmax. 口诀: 最后输出用softmax，其余基本都用relu

  3. 损失函数：

    categorical_crossentropy多分类对数损失

binary_crossentropy对数损失

mean_squared_error平均方差损失

mean_absolute_error平均绝对值损失
  4. 优化器：如SGD随机梯度下降, RMSProp, Adagrad, Adam, Adadelta等

9 种基本层模型：

  1. 3 种主模型：

    1. ‍全连接层Dense
    2. 卷积层：如conv1d, conv2d
    3. 循环层：如lstm, gru

  2. 3 种辅助层：

    1. Activation层
    2. Dropout层
    3. 池化层

  3. 3 种异构网络互联层：

    1. 嵌入层：用于第一层，输入数据到其他网络的转换
    2. Flatten层：用于卷积层到全连接层之间的过渡
    3. Permute层：用于RNN与CNN之间的接口

2. 五步法

五步法是用深度学习来解决问题的五个步骤：

  • 构造网络模型
  • 编译模型
  • 训练模型
  • 评估模型
  • 使用模型进行预测

在这五步之中，其实关键的步骤主要只有第一步，这一步确定了，后面的参数都可以根据它来设置.

2.1. 过程化方法构造网络模型

先从最容易理解的开始，过程化方法构造网络模型的过程.

Keras 中提供了 Sequential容器来实现过程式构造. 只要用 Sequential 的 add 方法把层结构加进来就可以了. 10种基本层结构会在后面详细讲.

例如：

from keras.models import Sequential
from keras.layers import Dense, Activation

model = Sequential()
model.add(Dense(units=64, input_dim=100))
model.add(Activation("relu"))
model.add(Dense(units=10))
model.add(Activation("softmax"))

对于什么样的问题构造什么样的层结构，会在后面的例子中介绍.

2.2. 编译模型

模型构造好之后，下一步就可以调用Sequential的compile方法来编译它.

model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

编译时需要指定两个基本元素：loss是损失函数，optimizer是优化函数.

如果只想用最基本的功能，只要指定字符串的名字就可以了. 如果想配置更多的参数，调用相应的类来生成对象.

例如：我们想为随机梯度下降配上Nesterov动量，就生成一个SGD的对象就好了：

from keras.optimizers import SGD
model.compile(loss='categorical_crossentropy', 
              optimizer=SGD(lr=0.01, momentum=0.9, nesterov=True))

lr是学习率，learning rate.

2.3. 训练模型

调用fit函数，将输出的值X，打好标签的值y，epochs训练轮数，batch_size批次大小设置一下就可以了：

model.fit(x_train, y_train, epochs=5, batch_size=32)

2.4. 评估模型

模型训练的好不好，训练数据不算数，需要用测试数据来评估一下：

loss_and_metrics = model.evaluate(x_test, y_test, batch_size=128)

2.5. 用模型来预测

一切训练的目的是在于预测：

classes = model.predict(x_test, batch_size=128)

3. 四种基本元素

3.1. 网络结构

主要用后面的层结构来拼装. 网络结构如何设计呢?

可以参考论文，比如这篇中不管是左边的19层的VGG-19，还是右边34层的resnet，只要按图去实现就好了.

image

3.2. 激活函数

  • 对于多分类的情况，最后一层是softmax.
  • 其它深度学习层中多用relu.
  • 二分类可以用sigmoid.
  • 另外浅层神经网络也可以用tanh.

3.3. 损失函数

  • categorical_crossentropy：多分类对数损失
  • binary_crossentropy：对数损失
  • mean_squared_error：均方差
  • mean_absolute_error：平均绝对值损失

对于多分类来说，主要用categorical_ crossentropy.

3.4. 优化器

  • SGD：随机梯度下降
  • Adagrad：Adaptive Gradient自适应梯度下降
  • Adadelta：对于Adagrad的进一步改进
  • RMSProp
  • Adam

本文将着重介绍后两种教程.

4. 深度学习中的函数式编程

前面介绍的各种基本层，除了可以add进Sequential容器串联之外，它们本身也是callable对象，被调用之后，返回的还是callable对象. 所以可以将它们视为函数，通过调用的方式来进行串联.

来个官方例子：

from keras.layers import Input, Dense
from keras.models import Model

inputs = Input(shape=(784,))

x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)

model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
             loss='categorical_crossentropy',
             metrics=['accuracy'])
model.fit(data, labels)

4.1. 为什么要用函数式编程？

答案是，复杂的网络结构并不是都是线性的 add 进容器中的. 并行的，重用的，什么情况都有. 这时候callable 的优势就发挥出来了.

比如下面的Google Inception模型，就是带并联的：

image

我们的代码自然是以并联应对并联了，一个输入input_img被三个模型所重用：

from keras.layers import Conv2D, MaxPooling2D, Input

input_img = Input(shape=(256, 256, 3))

tower_1 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3, 3), padding='same', activation='relu')(tower_1)

tower_2 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5, 5), padding='same', activation='relu')(tower_2)

tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(64, (1, 1), padding='same', activation='relu')(tower_3)

output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)

5. 案例教程

5.1. CNN处理MNIST手写识别

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
   x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
   x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
   input_shape = (1, img_rows, img_cols)
else:
   x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
   x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
   input_shape = (img_rows, img_cols, 1)
   
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# 首先解析一下核心模型代码，因为模型是线性的，还是用Sequential容器：
model = Sequential()
# 核心是两个卷积层
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
# 防止过拟合，加上一个最大池化层，再加上一个Dropout层
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 全连接层输出了，中间的数据转换需要一个Flatten层
model.add(Flatten())
# 全连接层，激活函数是relu. 
model.add(Dense(128, activation='relu'))
# 防止过拟合，再加一个Dropout层
model.add(Dropout(0.5))
# 最后，通过一个softmax激活函数的全连接网络输出
model.add(Dense(num_classes, activation='softmax'))

# 编译模型，
# 损失函数是 categorical_crossentropy多类对数损失函数
# 优化器选用 Adadelta
model.compile(loss=keras.losses.categorical_crossentropy,
             optimizer=keras.optimizers.Adadelta(),
             metrics=['accuracy'])
model.fit(x_train, y_train,
         batch_size=batch_size,
         epochs=epochs,
         verbose=1,
         validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

5.2. 机器翻译：多语种互译

英译汉，汉译英之类的事情，在学生时代是不是一直难为这你呢？ 现在不用担心了，只要有两种语言的对照表，我们就可以训练一个模型来像做一个机器翻译.

首先得下载一个字典：

http://www.manythings.org/anki/

机器翻译功能的完整实现：

from __future__ import print_function

from keras.models import Model
from keras.layers import Input, LSTM, Dense
import numpy as np

batch_size = 64  # Batch size for training.
epochs = 100     # Number of epochs to train for.
latent_dim = 256 # Latent dimensionality of the encoding space.
num_samples = 10000  # Number of samples to train on.
# Path to the data txt file on disk.
data_path = 'fra-eng/fra.txt'

# Vectorize the data.
input_texts = []
target_texts = []
input_characters = set()
target_characters = set()
with open(data_path, 'r', encoding='utf-8') as f:
   lines = f.read().split('\n')
for line in lines[: min(num_samples, len(lines) - 1)]:
   input_text, target_text = line.split('\t')
   # We use "tab" as the "start sequence" character
   # for the targets, and "\n" as "end sequence" character.
   target_text = '\t' + target_text + '\n'
   input_texts.append(input_text)
   target_texts.append(target_text)
   for char in input_text:
       if char not in input_characters:
           input_characters.add(char)
   for char in target_text:
       if char not in target_characters:
           target_characters.add(char)

input_characters = sorted(list(input_characters))
target_characters = sorted(list(target_characters))
num_encoder_tokens = len(input_characters)
num_decoder_tokens = len(target_characters)
max_encoder_seq_length = max([len(txt) for txt in input_texts])
max_decoder_seq_length = max([len(txt) for txt in target_texts])

print('Number of samples:', len(input_texts))
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Max sequence length for inputs:', max_encoder_seq_length)
print('Max sequence length for outputs:', max_decoder_seq_length)

input_token_index = dict(
   [(char, i) for i, char in enumerate(input_characters)])
target_token_index = dict(
   [(char, i) for i, char in enumerate(target_characters)])

encoder_input_data = np.zeros(
   (len(input_texts), max_encoder_seq_length, num_encoder_tokens),
   dtype='float32')
decoder_input_data = np.zeros(
   (len(input_texts), max_decoder_seq_length, num_decoder_tokens),
   dtype='float32')
decoder_target_data = np.zeros(
   (len(input_texts), max_decoder_seq_length, num_decoder_tokens),
   dtype='float32')

for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):
   for t, char in enumerate(input_text):
       encoder_input_data[i, t, input_token_index[char]] = 1.
   for t, char in enumerate(target_text):
       # decoder_target_data is ahead of decoder_input_data by one timestep
       decoder_input_data[i, t, target_token_index[char]] = 1.
       if t > 0:
           # decoder_target_data will be ahead by one timestep
           # and will not include the start character.
           decoder_target_data[i, t - 1, target_token_index[char]] = 1.

# Define an input sequence and process it.
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True) # RNN
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]

# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
                                    initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

# Run training
# 优化器选用rmsprop
# 损失函数是categorical_crossentropy
# validation_split是将一个集合随机分成训练集和测试集
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
         batch_size=batch_size,
         epochs=epochs,
         validation_split=0.2)
# Save model
model.save('s2s.h5')

encoder_model = Model(encoder_inputs, encoder_states)

decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(
   decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
   [decoder_inputs] + decoder_states_inputs,
   [decoder_outputs] + decoder_states)

# Reverse-lookup token index to decode sequences back to
# something readable.
reverse_input_char_index = dict(
   (i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict(
   (i, char) for char, i in target_token_index.items())


def decode_sequence(input_seq):
   # Encode the input as state vectors.
   states_value = encoder_model.predict(input_seq)

   # Generate empty target sequence of length 1.
   target_seq = np.zeros((1, 1, num_decoder_tokens))
   # Populate the first character of target sequence with the start character.
   target_seq[0, 0, target_token_index['\t']] = 1.

   # Sampling loop for a batch of sequences
   # (to simplify, here we assume a batch of size 1).
   stop_condition = False
   decoded_sentence = ''
   while not stop_condition:
       output_tokens, h, c = decoder_model.predict(
           [target_seq] + states_value)

       # Sample a token
       sampled_token_index = np.argmax(output_tokens[0, -1, :])
       sampled_char = reverse_target_char_index[sampled_token_index]
       decoded_sentence += sampled_char

       # Exit condition: either hit max length
       # or find stop character.
       if (sampled_char == '\n' or
          len(decoded_sentence) > max_decoder_seq_length):
           stop_condition = True

       # Update the target sequence (of length 1).
       target_seq = np.zeros((1, 1, num_decoder_tokens))
       target_seq[0, 0, sampled_token_index] = 1.

       # Update states
       states_value = [h, c]

   return decoded_sentence


for seq_index in range(100):
   # Take one sequence (part of the training set)
   # for trying out decoding.
   input_seq = encoder_input_data[seq_index: seq_index + 1]
   decoded_sentence = decode_sequence(input_seq)
   print('-')
   print('Input sentence:', input_texts[seq_index])
   print('Decoded sentence:', decoded_sentence)

作者简介

刘子瑛，阿里巴巴操作系统框架专家；CSDN 博客专家. 工作十余年，一直对数学与人工智能算法相关、新编程语言、新开发方法等相关领域保持浓厚的兴趣. 乐于通过技术分享促进新技术进步.

作者博客

https://blog.csdn.net/lusing/article/details/8057327

Last modification：April 24th, 2019 at 09:30 pm
© 允许规范转载