基于Keras的attention实战

要点：
该教程为基于Kears的Attention实战，环境配置：
Wn10+CPU i7-6700
Pycharm 2018
python 3.6
numpy 1.14.5
Keras 2.0.2
Matplotlib 2.2.2
强调：各种库的版本型号一定要配置对，因为Keras以及Tensorflow升级更新比较频繁，很多函数更新后要么更换了名字，要么没有这个函数了，所以大家务必重视。
相关代码我放在了我的代码仓库里哈，欢迎大家下载，这里附上地址：基于Kears的Attention实战
笔者信息：Next_Legend QQ:1219154092 人工智能 自然语言处理 图像处理 神经网络
——2018.8.21于天津大学

---

一、导读

最近两年，尤其在今年，注意力机制(Attention)及其变种Attention逐渐热了起来，在很多顶会Paper中都或多或少的用到了attention,所以小编出于好奇，整理了这篇基于Kears的Attention实战，本教程仅从代码的角度来看Attention。通过一个简单的例子，探索Attention机制是如何在模型中起到特征选择作用的。

二、代码实战（一）

1、导入相关库文件

import numpy as np
from attention_utils import get_activations, get_data

np.random.seed(1337)  # for reproducibility
from keras.models import *
from keras.layers import Input, Dense, merge
import tensorflow as tf

2、数据生成函数

def get_data(n, input_dim, attention_column=1):
    """
    Data generation. x is purely random except that it's first value equals the target y.
    In practice, the network should learn that the target = x[attention_column].
    Therefore, most of its attention should be focused on the value addressed by attention_column.
    :param n: the number of samples to retrieve.
    :param input_dim: the number of dimensions of each element in the series.
    :param attention_column: the column linked to the target. Everything else is purely random.
    :return: x: model inputs, y: model targets
    """
    x = np.random.standard_normal(size=(n, input_dim))
    y = np.random.randint(low=0, high=2, size=(n, 1))
    x[:, attention_column] = y[:, 0]
    return x, y

3、模型定义函数

将输入进行一次变换后，计算出Attention权重，将输入乘上Attention权重，获得新的特征。

def build_model():
    inputs = Input(shape=(input_dim,))

    # ATTENTION PART STARTS HERE
    attention_probs = Dense(input_dim, activation='softmax', name='attention_vec')(inputs)
    attention_mul =merge([inputs, attention_probs], output_shape=32, name='attention_mul', mode='mul')
    # ATTENTION PART FINISHES HERE

    attention_mul = Dense(64)(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model

4、主函数

if __name__ == '__main__':
    N = 10000
    inputs_1, outputs = get_data(N, input_dim)

    m = build_model()
    m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    print(m.summary())

    m.fit([inputs_1], outputs, epochs=20, batch_size=64, validation_split=0.5)

    testing_inputs_1, testing_outputs = get_data(1, input_dim)

    # Attention vector corresponds to the second matrix.
    # The first one is the Inputs output.
    attention_vector = get_activations(m, testing_inputs_1,
                                       print_shape_only=True,
                                       layer_name='attention_vec')[0].flatten()
    print('attention =', attention_vector)

    # plot part.
    import matplotlib.pyplot as plt
    import pandas as pd

    pd.DataFrame(attention_vector, columns=['attention (%)']).plot(kind='bar',
                                                                   title='Attention Mechanism as '
                                                                         'a function of input'
                                                                         ' dimensions.')
    plt.show()

5、运行结果

代码中，attention_column为1，也就是说，label只与数据的第1个特征相关。从运行结果中可以看出，Attention权重成功地获取了这个信息。

---

三、代码实战（二）

1、导入相关库文件

from keras.layers import merge
from keras.layers.core import *
from keras.layers.recurrent import LSTM
from keras.models import *

from attention_utils import get_activations, get_data_recurrent
INPUT_DIM = 2
TIME_STEPS = 20
# if True, the attention vector is shared across the input_dimensions where the attention is applied.
SINGLE_ATTENTION_VECTOR = False
APPLY_ATTENTION_BEFORE_LSTM = False

2、数据生成函数

def attention_3d_block(inputs):
    # inputs.shape = (batch_size, time_steps, input_dim)
    input_dim = int(inputs.shape[2])
    a = Permute((2, 1))(inputs)
    a = Reshape((input_dim, TIME_STEPS))(a) # this line is not useful. It's just to know which dimension is what.
    a = Dense(TIME_STEPS, activation='softmax')(a)
    if SINGLE_ATTENTION_VECTOR:
        a = Lambda(lambda x: K.mean(x, axis=1), name='dim_reduction')(a)
        a = RepeatVector(input_dim)(a)
    a_probs = Permute((2, 1), name='attention_vec')(a)
    output_attention_mul = merge([inputs, a_probs], name='attention_mul', mode='mul')
    return output_attention_mul

def model_attention_applied_after_lstm():
    inputs = Input(shape=(TIME_STEPS, INPUT_DIM,))
    lstm_units = 32
    lstm_out = LSTM(lstm_units, return_sequences=True)(inputs)
    attention_mul = attention_3d_block(lstm_out)
    attention_mul = Flatten()(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model

def model_attention_applied_before_lstm():
    inputs = Input(shape=(TIME_STEPS, INPUT_DIM,))
    attention_mul = attention_3d_block(inputs)
    lstm_units = 32
    attention_mul = LSTM(lstm_units, return_sequences=False)(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model

4、主函数

 if __name__ == '__main__':

    N = 300000
    # N = 300 -> too few = no training
    inputs_1, outputs = get_data_recurrent(N, TIME_STEPS, INPUT_DIM)

    if APPLY_ATTENTION_BEFORE_LSTM:
        m = model_attention_applied_before_lstm()
    else:
        m = model_attention_applied_after_lstm()

    m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    print(m.summary())

    m.fit([inputs_1], outputs, epochs=1, batch_size=64, validation_split=0.1)

    attention_vectors = []
    for i in range(300):
        testing_inputs_1, testing_outputs = get_data_recurrent(1, TIME_STEPS, INPUT_DIM)
        attention_vector = np.mean(get_activations(m,
                                                   testing_inputs_1,
                                                   print_shape_only=True,
                                                   layer_name='attention_vec')[0], axis=2).squeeze()
        print('attention =', attention_vector)
        assert (np.sum(attention_vector) - 1.0) < 1e-5
        attention_vectors.append(attention_vector)

    attention_vector_final = np.mean(np.array(attention_vectors), axis=0)
    # plot part.
    import matplotlib.pyplot as plt
    import pandas as pd

    pd.DataFrame(attention_vector_final, columns=['attention (%)']).plot(kind='bar',
                                                                         title='Attention Mechanism as '
                                                                               'a function of input'
                                                                               ' dimensions.')
    plt.show()

相关代码放在代码仓库里哈，欢迎大家下载，这里附上地址：基于Kears的Attention实战