程序员学深度学习快速入门五步法

作为一个程序员，我们可以像学习编程一样学习深度学习模型开发。我们以Keras为例来说明。

我们可以用5步 + 4种基本元素 + 9种基本层结构，这5-4-9模型来总结。

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

包括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

3种辅助层：
1. Activation层
2. Dropout层
3. 池化层

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

我们通过一张图来理解下它们之间的关系

五步法

五步法是用深度学习来解决问题的五个步骤：
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

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。

过程化方法构造网络模型

我们先学习最容易理解的，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种基本层结构我们会在后面详细讲。

例：

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，我们会在后面的例子中介绍。

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：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。这几个概念我们在《Tensorflow快餐教程(7) - 梯度下降》中曾经介绍过，需要复习的同学可以移步。

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)

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)

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)

4种基本元素

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。

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。

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。

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

前三种在《Tensorflow快餐教程(7) - 梯度下降》中已经介绍过，后两种在后面的教程中会补充介绍。

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)

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：

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)

案例教程

CNN处理MNIST手写识别

光说不练是假把式。我们来看看符合五步法的处理MNIST的例子。

首先解析一下核心模型代码，因为模型是线性的，我们还是用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'))

为了防止过拟合，我们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))

下面要进入全连接层输出了，这两个中间的数据转换需要一个Flatten层：

model.add(Flatten())

下面是全连接层，激活函数是relu。
还怕过拟合，再来个Dropout层！

model.add(Dense(128, activation='relu'))
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'))

下面是编译这个模型，损失函数是categorical_crossentropy多类对数损失函数，优化器选用Adadelta，我们在《Tensorflow快餐教程(7) - 梯度下降》中有过介绍。

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

下面是可以运行的完整代码：

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)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

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])

MNIST的例子实在用了太多遍了，我也有点不好意思了。下面我们来个surprise，处理一下各种语言之间的翻译！

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/

然后我们还是老办法，我们先看一下核心代码。没啥说的，这类序列化处理的问题用的一定是RNN，通常都是用LSTM.
下面就是用LSTM建模的过程：

encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
encoder_states = [state_h, state_c]

decoder_inputs = Input(shape=(None, num_decoder_tokens))
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)

model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

优化器选用rmsprop，损失函数还是categorical_crossentropy.
validation_split是将一个集合随机分成训练集和测试集。

# Run training
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)

最后，训练一个模型不容易，我们将其存储起来。

model.save('s2s.h5')

下面是完整的实现了机器翻译功能的代码，加上注释和空行其实也就不过100多行：

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)
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
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)

翻译结果输出如下，是不是很好玩？

Input sentence: Let's go!
Decoded sentence: 我們開始吧！

-
Input sentence: Look out!
Decoded sentence: 当心！

-
Input sentence: She runs.
Decoded sentence: 她在行走。

-
Input sentence: Stand up.
Decoded sentence: 起立。

-
Input sentence: They won.
Decoded sentence: 他们赢了。

-
Input sentence: Tom died.
Decoded sentence: 汤姆去世了。

-
Input sentence: Tom quit.
Decoded sentence: 汤姆不干了。

-
Input sentence: Tom swam.
Decoded sentence: 汤姆游泳了。

-
Input sentence: Trust me.
Decoded sentence: 相信我。

-
Input sentence: Try hard.
Decoded sentence: 努力。

前情提要

Tensorflow快餐教程(1) - 30行代码搞定手写识别: https://blog.csdn.net/lusing/article/details/79965160
Tensorflow快餐教程(2) - 标量计算: https://blog.csdn.net/lusing/article/details/79980808
Tensorflow快餐教程(3) - 向量: https://blog.csdn.net/lusing/article/details/80054716
Tensorflow快餐教程(4) - 矩阵: https://blog.csdn.net/lusing/article/details/80071169
Tensorflow快餐教程(5) - 范数: https://blog.csdn.net/lusing/article/details/80082235
Tensorflow快餐教程(6) - 矩阵分解: https://blog.csdn.net/lusing/article/details/80113583
Tensorflow快餐教程(7) - 梯度下降: https://blog.csdn.net/lusing/article/details/80178069
Tensorflow快餐教程(8) - 深度学习简史：https://blog.csdn.net/lusing/article/details/80182063
Tensorflow快餐教程(9) - 卷积: https://blog.csdn.net/lusing/article/details/80199015
Tensorflow快餐教程(10) - 循环神经网络: https://blog.csdn.net/lusing/article/details/80246226
Tensorflow快餐教程(11) - 不懂机器学习就只调API行不行？: https://mp.csdn.net/mdeditor/80369607
Tensorflow快餐教程(12) - 用机器写莎士比亚的戏剧: https://blog.csdn.net/lusing/article/details/80502056