Machine learning LSTM后接平均池
我正在使用Keras 1.0。我的问题与这个问题相同(),但那里的答案对我来说似乎不够 我想实现这个网络: 以下代码不起作用:Machine learning LSTM后接平均池,machine-learning,neural-network,deep-learning,keras,recurrent-neural-network,Machine Learning,Neural Network,Deep Learning,Keras,Recurrent Neural Network,我正在使用Keras 1.0。我的问题与这个问题相同(),但那里的答案对我来说似乎不够 我想实现这个网络: 以下代码不起作用: sequence = Input(shape=(max_sent_len,), dtype='int32') embedded = Embedding(vocab_size, word_embedding_size)(sequence) lstm = LSTM(hidden_state_size, activation='sigmoid', inner_activat
sequence = Input(shape=(max_sent_len,), dtype='int32')
embedded = Embedding(vocab_size, word_embedding_size)(sequence)
lstm = LSTM(hidden_state_size, activation='sigmoid', inner_activation='hard_sigmoid', return_sequences=True)(embedded)
pool = AveragePooling1D()(lstm)
output = Dense(1, activation='sigmoid')(pool)
如果我没有设置return\u sequences=True
,我在调用averagepoolg1d()
时会出现此错误:
添加
TimeDistributed(密集(1))
有助于:
sequence = Input(shape=(max_sent_len,), dtype='int32')
embedded = Embedding(vocab_size, word_embedding_size)(sequence)
lstm = LSTM(hidden_state_size, activation='sigmoid', inner_activation='hard_sigmoid', return_sequences=True)(embedded)
distributed = TimeDistributed(Dense(1))(lstm)
pool = AveragePooling1D()(distributed)
output = Dense(1, activation='sigmoid')(pool)
我认为公认的答案基本上是错误的。在以下位置找到了解决方案: 但是,它只适用于theano后端。我修改了代码,使其同时支持theano和tensorflow
from keras.engine.topology import Layer, InputSpec
from keras import backend as T
class TemporalMeanPooling(Layer):
"""
This is a custom Keras layer. This pooling layer accepts the temporal
sequence output by a recurrent layer and performs temporal pooling,
looking at only the non-masked portion of the sequence. The pooling
layer converts the entire variable-length hidden vector sequence
into a single hidden vector, and then feeds its output to the Dense
layer.
input shape: (nb_samples, nb_timesteps, nb_features)
output shape: (nb_samples, nb_features)
"""
def __init__(self, **kwargs):
super(TemporalMeanPooling, self).__init__(**kwargs)
self.supports_masking = True
self.input_spec = [InputSpec(ndim=3)]
def get_output_shape_for(self, input_shape):
return (input_shape[0], input_shape[2])
def call(self, x, mask=None): #mask: (nb_samples, nb_timesteps)
if mask is None:
mask = T.mean(T.ones_like(x), axis=-1)
ssum = T.sum(x,axis=-2) #(nb_samples, np_features)
mask = T.cast(mask,T.floatx())
rcnt = T.sum(mask,axis=-1,keepdims=True) #(nb_samples)
return ssum/rcnt
#return rcnt
def compute_mask(self, input, mask):
return None
谢谢,我也遇到了这个问题,但是我认为时间分布层没有按照你想要的那样工作,你可以试试Luke Guye的临时意义池层,它对我很有用。以下是一个例子:
sequence = Input(shape=(max_sent_len,), dtype='int32')
embedded = Embedding(vocab_size, word_embedding_size)(sequence)
lstm = LSTM(hidden_state_size, return_sequences=True)(embedded)
pool = TemporalMeanPooling()(lstm)
output = Dense(1, activation='sigmoid')(pool)
我刚刚尝试实现与原始海报相同的模型,我使用的是
keras2.0.3
。当我使用globalaveragepoolg1d
时,LSTM后的平均池工作正常,只需确保LSTM层中的return\u sequences=True
。试试看 派对已经很晚了,但是tf.keras.layers.averagepoolg1d
以及合适的pool\u size
参数似乎也返回了正确的结果
正在处理由共享的示例
#创建示例数据
A=np.数组([[1,2,3],[4,5,6],[0,0,0],[0,0,0],[0,0,0])
B=np.数组([[1,3,0],[4,0,0],[0,0,1],[0,0,0],[0,0,0])
C=np.array([A,B]).astype(“float32”)
#预期答案(对于时间平均值)
平均值(C,轴=1)
输出是
数组([[1,1.4,1.8],
[1,0.6,0.2]],数据类型=32)
现在使用averagepoolg1d
model=keras.models.Sequential(
tf.keras.layers.AveragePoolg1d(池大小=5)
)
模型预测(C)
输出是,
数组([[1,1.4,1.8]],
[[1,0.6,0.2]],数据类型=float32)
<有些>要考虑,
应等于重复层的步长/时间步长大小pool_size
- 输出的形状为
,其中包含一个额外的(批量大小、下采样步骤、特征)
维度。如果将循环层中的下采样步骤
设置为等于timestep size,则该值将始终为1pool_size
from keras.engine.topology import Layer, InputSpec
from keras import backend as T
class TemporalMeanPooling(Layer):
"""
This is a custom Keras layer. This pooling layer accepts the temporal
sequence output by a recurrent layer and performs temporal pooling,
looking at only the non-masked portion of the sequence. The pooling
layer converts the entire variable-length hidden vector sequence
into a single hidden vector, and then feeds its output to the Dense
layer.
input shape: (nb_samples, nb_timesteps, nb_features)
output shape: (nb_samples, nb_features)
"""
def __init__(self, **kwargs):
super(TemporalMeanPooling, self).__init__(**kwargs)
self.supports_masking = True
self.input_spec = [InputSpec(ndim=3)]
def get_output_shape_for(self, input_shape):
return (input_shape[0], input_shape[2])
def call(self, x, mask=None): #mask: (nb_samples, nb_timesteps)
if mask is None:
mask = T.mean(T.ones_like(x), axis=-1)
ssum = T.sum(x,axis=-2) #(nb_samples, np_features)
mask = T.cast(mask,T.floatx())
rcnt = T.sum(mask,axis=-1,keepdims=True) #(nb_samples)
return ssum/rcnt
#return rcnt
def compute_mask(self, input, mask):
return None
sequence = Input(shape=(max_sent_len,), dtype='int32')
embedded = Embedding(vocab_size, word_embedding_size)(sequence)
lstm = LSTM(hidden_state_size, return_sequences=True)(embedded)
pool = TemporalMeanPooling()(lstm)
output = Dense(1, activation='sigmoid')(pool)