class BiLstmSelfAttention(Layer):
def __init__(self, output_dim, **kwargs):
self.output_dim = output_dim
super(BiLstmSelfAttention, self).__init__(**kwargs)
def build(self, input_shape):
# 为该层创建一个可训练的权重
# inputs.shape = (batch_size, time_steps, seq_len)
self.kernel = self.add_weight(name='kernel',
shape=(3, input_shape[2], self.output_dim),
initializer='uniform',
trainable=True)
super(BiLstmSelfAttention, self).build(input_shape) # 一定要在最后调用它
def call(self, x):
print("kernel.shape", self.kernel.shape)
print("kernel[0].shape", self.kernel[0].shape)
print("x.shape", x.shape)
WQ = K.dot(x, self.kernel[0])
WK = K.dot(x, self.kernel[1])
WV = K.dot(x, self.kernel[2])
print("WQ.shape", WQ.shape)
print("K.permute_dimensions(WK, [0, 2, 1]).shape", K.permute_dimensions(WK, [0, 2, 1]).shape)
QK = K.batch_dot(WQ, K.permute_dimensions(WK, [0, 2, 1]))
QK = QK / (self.output_dim ** 0.5)
QK = K.softmax(QK)
print("QK.shape", QK.shape)
V = K.batch_dot(QK, WV)
return V
def compute_output_shape(self, input_shape):
return (input_shape[0], input_shape[1], self.output_dim)
Traceback (most recent call last):
File "/usr/idip/.local/lib/python3.7/site-packages/tensorflow/python/framework/tensor_util.py", line 558, in make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/idip/.local/lib/python3.7/site-packages/tensorflow/python/framework/tensor_util.py", line 558, in <listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/idip/.local/lib/python3.7/site-packages/tensorflow/python/util/compat.py", line 61, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got 3
