Keras的注意事项：如何在keras密集层中添加不同的注意机制？

Question

我是Keras的新手，我正在尝试使用注意层在keras中构建一个简单的自动编码器：

这是我尝试过的：

data = Input(shape=(w,), dtype=np.float32, name='input_da')
noisy_data = Dropout(rate=0.2, name='drop1')(data)

encoded = Dense(256, activation='relu',
            name='encoded1', **kwargs)(noisy_data)
encoded = Lambda(mvn, name='mvn1')(encoded)

encoded = Dense(128, activation='relu',
            name='encoded2', **kwargs)(encoded)

encoded = Lambda(mvn, name='mvn2')(encoded)
encoded = Dropout(rate=0.5, name='drop2')(encoded)


encoder = Model([data], encoded)
encoded1 = encoder.get_layer('encoded1')
encoded2 = encoder.get_layer('encoded2')


decoded = DenseTied(256, tie_to=encoded2, transpose=True,
            activation='relu', name='decoded2')(encoded)
decoded = Lambda(mvn, name='new_mv')(decoded)


decoded = DenseTied(w, tie_to=encoded1, transpose=True,
            activation='linear', name='decoded1')(decoded)

它看起来像这样：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
data (InputLayer)            (None, 2693)              0         
_________________________________________________________________
drop1 (Dropout)              (None, 2693)              0         
_________________________________________________________________
encoded1 (Dense)             (None, 256)               689664    
_________________________________________________________________
mvn1 (Lambda)                (None, 256)               0         
_________________________________________________________________
encoded2 (Dense)             (None, 128)               32896     
_________________________________________________________________
mvn2 (Lambda)                (None, 128)               0         
_________________________________________________________________
drop2 (Dropout)              (None, 128)               0         
_________________________________________________________________
decoded2 (DenseTied)         (None, 256)               256       
_________________________________________________________________
mvn3 (Lambda)                (None, 256)               0         
_________________________________________________________________
decoded1 (DenseTied)         (None, 2693)              2693      
=================================================================

我可以在这个模型中添加注意层？ 我应该在第一次编码输出后和第二次编码输入之前添加吗？

encoded = Lambda(mvn, name='mvn1')(encoded)

    Here?

encoded = Dense(128, activation='relu',
            name='encoded2', **kwargs)(encoded)

我也想去看看这个美丽的书：

https://github.com/Cyber​​ZHG/keras-self-attention

他们已经实现了各种类型的注意机制，但它适用于顺序模型。 我如何在模型中添加这些注意力？

我试着非常简单地注意：

encoded = Dense(256, activation='relu',
        name='encoded1', **kwargs)(noisy_data)


encoded = Lambda(mvn, name='mvn1')(encoded)

attention_probs = Dense(256, activation='softmax', name='attention_vec')(encoded)
attention_mul = multiply([encoded, attention_probs], name='attention_mul')
attention_mul = Dense(256)(attention_mul)

print(attention_mul.shape)

encoded = Dense(128, activation='relu',
        name='encoded2', **kwargs)(attention_mul)

它是在正确的位置，我可以添加任何其他注意机制与此模型？

Answer 1

我猜你正在做的是一种增加注意力的正确方法，因为注意力本身就不过是可以被视为一个密集层的权重。 此外，我想在编码器之后应用注意力是正确的事情，因为它会将注意力集中在您的任务所需的数据分布的“信息性”部分。