如果您想关注时间维度，那么这段代码对我来说似乎是正确的:

If you want to have an attention along the time dimension, then this part of your code seems correct to me:

activations = LSTM(units, return_sequences=True)(embedded)

# compute importance for each step
attention = Dense(1, activation='tanh')(activations)
attention = Flatten()(attention)
attention = Activation('softmax')(attention)
attention = RepeatVector(units)(attention)
attention = Permute([2, 1])(attention)

sent_representation = merge([activations, attention], mode='mul')

您已经计算出形状为(batch_size, max_length)的注意力向量:

You've worked out the attention vector of shape (batch_size, max_length):

attention = Activation('softmax')(attention)

我以前从未看过这段代码，所以我不能说这个代码是否正确:

I've never seen this code before, so I can't say if this one is actually correct or not:

K.sum(xin, axis=-2)

进一步阅读(您可以看看):

Further reading (you might have a look):

• https://github.com/philipperemy/keras-visualize-activations

https://github.com/philipperemy/keras-attention-mechanism