LSTM+Attention代码

最新推荐文章于 2024-05-13 08:51:10 发布

AI强仔

最新推荐文章于 2024-05-13 08:51:10 发布

阅读量1.2k

点赞数 3

分类专栏：神经网络 Attention 文章标签： lstm keras 深度学习

本文链接：https://blog.csdn.net/zephyr_wang/article/details/125340569

版权

神经网络同时被 2 个专栏收录

24 篇文章 1 订阅

订阅专栏

Attention

6 篇文章 0 订阅

订阅专栏

from keras.layers import LSTM,SpatialDropout1D
from keras import initializers, regularizers, constraints
from keras.layers import Bidirectional

Attention

class Attention(Layer):
    def __init__(self, step_dim,
                 W_regularizer=None, b_regularizer=None,
                 W_constraint=None, b_constraint=None,
                 bias=True, **kwargs):
        self.supports_masking = True
        self.init = initializers.get('glorot_uniform')

        self.W_regularizer = regularizers.get(W_regularizer)
        self.b_regularizer = regularizers.get(b_regularizer)

        self.W_constraint = constraints.get(W_constraint)
        self.b_constraint = constraints.get(b_constraint)

        self.bias = bias
        self.step_dim = step_dim
        self.features_dim = 0
        super(Attention, self).__init__(**kwargs)

    def build(self, input_shape):
        assert len(input_shape) == 3

        self.W = self.add_weight(shape=(input_shape[-1],),
                                 initializer=self.init,
                                  name='{}_W'.format(self.name),
                                 regularizer=self.W_regularizer,
                                 constraint=self.W_constraint)
        self.features_dim = input_shape[-1]

        if self.bias:
            self.b = self.add_weight(shape=(input_shape[1],),
                                     initializer='zero',
                                     name='{}_b'.format(self.name),
                                     regularizer=self.b_regularizer,
                                     constraint=self.b_constraint)
        else:
            self.b = None

        self.built = True

    def compute_mask(self, input, input_mask=None):
        return None

    def call(self, x, mask=None):
        features_dim = self.features_dim
        step_dim = self.step_dim

        eij = K.reshape(K.dot(K.reshape(x, (-1, features_dim)),
                        K.reshape(self.W, (features_dim, 1))), (-1, step_dim))

        if self.bias:
            eij += self.b

        eij = K.tanh(eij)

        a = K.exp(eij)

        if mask is not None:
            a *= K.cast(mask, K.floatx())

        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())

        a = K.expand_dims(a)
        weighted_input = x * a
        return K.sum(weighted_input, axis=1)

    def compute_output_shape(self, input_shape):
        return input_shape[0],  self.features_dim

神经网络

x_msgtoken= keras.layers.Embedding(len(embedding_weights), embed_size,mask_zero=True,
                                       weights=[embedding_weights],
                                       input_length=MAX_TOKEN_LEN,
                                       trainable=False)(inputs[2])
x_msgtoken = SpatialDropout1D(0.2)(x_msgtoken)
x_msgtoken = Bidirectional(LSTM(64, return_sequences=True))(x_msgtoken)
x_msgtoken= Bidirectional(LSTM(32, return_sequences=True))(x_msgtoken)
x_msgtoken = Attention(maxlen)(x_msgtoken)
x_msgtoken = Dense(64)(x_msgtoken)