本文介绍了如何将注意力层添加到 Bi-LSTM的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
我正在开发一个 Bi-LSTM 模型并想为其添加一个注意力层.但我不知道如何添加它.
I am developing a Bi-LSTM model and want to add a attention layer to it. But I am not getting how to add it.
我当前的模型代码是
model = Sequential()
model.add(Embedding(max_words, 1152, input_length=max_len, weights=[embeddings]))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Bidirectional(LSTM(32)))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.summary()
模型摘要是
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_1 (Embedding) (None, 1152, 1152) 278396928
_________________________________________________________________
batch_normalization_1 (Batch (None, 1152, 1152) 4608
_________________________________________________________________
activation_1 (Activation) (None, 1152, 1152) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 1152, 1152) 0
_________________________________________________________________
bidirectional_1 (Bidirection (None, 64) 303360
_________________________________________________________________
batch_normalization_2 (Batch (None, 64) 256
_________________________________________________________________
activation_2 (Activation) (None, 64) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_1 (Dense) (None, 1) 65
=================================================================
Total params: 278,705,217
Trainable params: 278,702,785
Non-trainable params: 2,432
推荐答案
这可以是一个可能的自定义解决方案,其中包含计算位置/时间维度上的注意力的自定义层
This can be a possible custom solution with a custom layer that computes attention on the positional/temporal dimension
from tensorflow.keras.layers import Layer
from tensorflow.keras import backend as K
class Attention(Layer):
def __init__(self, return_sequences=True):
self.return_sequences = return_sequences
super(Attention,self).__init__()
def build(self, input_shape):
self.W=self.add_weight(name="att_weight", shape=(input_shape[-1],1),
initializer="normal")
self.b=self.add_weight(name="att_bias", shape=(input_shape[1],1),
initializer="zeros")
super(Attention,self).build(input_shape)
def call(self, x):
e = K.tanh(K.dot(x,self.W)+self.b)
a = K.softmax(e, axis=1)
output = x*a
if self.return_sequences:
return output
return K.sum(output, axis=1)
它的构建是为了接收 3D 张量并输出 3D 张量 (return_sequences=True)
或 2D 张量 (return_sequences=False)
.下面是一个虚拟示例
it's build to receive 3D tensors and output 3D tensors (return_sequences=True)
or 2D tensors (return_sequences=False)
. below a dummy example
# dummy data creation
max_len = 100
max_words = 333
emb_dim = 126
n_sample = 5
X = np.random.randint(0,max_words, (n_sample,max_len))
Y = np.random.randint(0,2, n_sample)
使用 return_sequences=True
model = Sequential()
model.add(Embedding(max_words, emb_dim, input_length=max_len))
model.add(Bidirectional(LSTM(32, return_sequences=True)))
model.add(Attention(return_sequences=True)) # receive 3D and output 3D
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
model.summary()
model.compile('adam', 'binary_crossentropy')
model.fit(X,Y, epochs=3)
使用 return_sequences=False
model = Sequential()
model.add(Embedding(max_words, emb_dim, input_length=max_len))
model.add(Bidirectional(LSTM(32, return_sequences=True)))
model.add(Attention(return_sequences=False)) # receive 3D and output 2D
model.add(Dense(1, activation='sigmoid'))
model.summary()
model.compile('adam', 'binary_crossentropy')
model.fit(X,Y, epochs=3)
您可以轻松地将其集成到您的网络中
You can integrate it into your networks easily
这里正在运行的笔记本
这篇关于如何将注意力层添加到 Bi-LSTM的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!