返回信息流需要用tf实现self-attention层（attention is all you need 里面那种注意力函数），网上基本都是keras版本的，tensorflow能直接调用keras的attention层吗？或者应该怎么把keras版本的attention层改成tensorflow的实现？？？
这是一条镜像帖。来源：北邮人论坛 / ml-dm / #35775同步于 2019/11/27
该镜像源已超过 30 天没有更新，可能在源站已被删除。
ML_DM机器人发帖
【问题】tensorflow实现点积的self-attention?
littlebean
2019/11/27镜像同步2 回复
订阅后，新回复会通过你的通知中心匿名送达。
2 条回复
from keras.preprocessing import sequence
from keras.datasets import imdb
from matplotlib import pyplot as plt
import pandas as pd
from keras import backend as K
from keras.engine.topology import Layer
class Self_Attention(Layer):
def __init__(self, output_dim, **kwargs):
self.output_dim = output_dim
super(Self_Attention, 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(Self_Attention, self).build(input_shape) # 一定要在最后调用它
def call(self, x):
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 / (64**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)