解读注意力机制原理，教你使用Python实现深度学习模型

pip install tensorflow

import tensorflow as tf
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing.sequence import pad_sequences

# 加载 IMDB 数据集
max_features = 10000  # 仅使用数据集中前 10000 个最常见的单词
max_len = 200  # 每个评论的最大长度

(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)

# 将每个评论填充/截断为 max_len 长度
x_train = pad_sequences(x_train, maxlen=max_len)
x_test = pad_sequences(x_test, maxlen=max_len)

from tensorflow.keras.layers import Layer
import tensorflow.keras.backend as K

class Attention(Layer):
    def __init__(self, **kwargs):
        super(Attention, self).__init__(**kwargs)

    def build(self, input_shape):
        self.W = self.add_weight(name='attention_weight', shape=(input_shape[-1], input_shape[-1]), initializer='glorot_uniform', trainable=True)
        self.b = self.add_weight(name='attention_bias', shape=(input_shape[-1],), initializer='zeros', trainable=True)
        super(Attention, self).build(input_shape)

    def call(self, x):
        # 打分函数
        e = K.tanh(K.dot(x, self.W) + self.b)
        # 计算注意力权重
        a = K.softmax(e, axis=1)
        # 加权求和
        output = x * a
        return K.sum(output, axis=1)

    def compute_output_shape(self, input_shape):
        return input_shape[0], input_shape[-1]

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, LSTM, Dense

# 构建模型
model = Sequential()
model.add(Embedding(input_dim=max_features, output_dim=128, input_length=max_len))
model.add(LSTM(64, return_sequences=True))
model.add(Attention())
model.add(Dense(1, activation='sigmoid'))

# 编译模型
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# 训练模型
history = model.fit(x_train, y_train, epochs=5, batch_size=32, validation_split=0.2)

# 评估模型
test_loss, test_acc = model.evaluate(x_test, y_test)
print(f'Test Accuracy: {test_acc}')