2

我一直在使用 BiLSTM 对句子中的每个单词进行分类，我的输入是 n_sentences、max_sequence_length、classes。最近一直在尝试使用这个注意力层：https ://www.kaggle.com/takuok/bidirectional-lstm-and-attention-lb-0-043

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((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((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

我的输出需要是（样本、步骤、功能），否则我得到这个

ValueError: Error when checking target: expected dense_2 to have 2 dimensions, but got array with shape (656, 109, 2)

所以我换了：

 return input_shape[0], self.features_dim

至

 return input_shape[0], self.step_dim, self.features_dim

这样做我得到另一个错误：

InvalidArgumentError: Incompatible shapes: [32,109] vs. [32]
 [[{{node metrics/acc/Equal}}]]

我需要修改什么才能在我的句子上实际使用注意力层？

4

1 回答 1

0

你在使用 SeqSelfAttention 吗？

我遇到了同样的问题，我使用了 SeqWeightedAttention 而不是 SeqSelfAttention - 它解决了我的问题。

model.add(SeqWeightedAttention())
于 2019-11-09T23:45:07.453 回答