[英]Cannot import name 'Merge' from 'keras.layers'
I have try run a code but I find a problem with merge layers of Keras
.我尝试运行代码,但我发现Keras
合并层有问题。 I'm using python 3 and keras
2.2.4我正在使用 python 3 和keras
2.2.4
This is de code part of code这是代码的 de code 部分
import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import LSTM, Embedding, TimeDistributed, Dense, RepeatVector, Merge, Activation
from keras.preprocessing import image, sequence
import cPickle as pickle
def create_model(self, ret_model = False):
image_model = Sequential()
image_model.add(Dense(EMBEDDING_DIM, input_dim = 4096, activation='relu'))
image_model.add(RepeatVector(self.max_length))
lang_model = Sequential()
lang_model.add(Embedding(self.vocab_size, 256, input_length=self.max_length))
lang_model.add(LSTM(256,return_sequences=True))
lang_model.add(TimeDistributed(Dense(EMBEDDING_DIM)))
model = Sequential()
model.add(Merge([image_model, lang_model], mode='concat'))
model.add(LSTM(1000,return_sequences=False))
model.add(Dense(self.vocab_size))
model.add(Activation('softmax'))
print ("Model created!")
This is the message of error这是错误信息
from keras.layers import LSTM, Embedding, TimeDistributed, Dense, RepeatVector, Merge, Activation
ImportError: cannot import name 'Merge' from 'keras.layers'
Merge
is not supported in Keras +2. Keras +2 不支持Merge
。 Instead, you need to use Concatenate
layer:相反,您需要使用Concatenate
层:
merged = Concatenate()([x1, x2]) # NOTE: the layer is first constructed and then it's called on its input
or it's equivalent functional interface concatenate
(starting with lowercase c
):或者它是等效的功能接口concatenate
(以小写c
开头):
merged = concatenate([x1,x2]) # NOTE: the input of layer is passed as an argument, hence named *functional interface*
If you are interested in other forms of merging, eg addition, subtration, etc., then you can use the relevant layers.如果您对其他形式的合并感兴趣,例如加法、减法等,那么您可以使用相关层。 See the documentation for a comprehensive list of merge layers.有关合并图层的完整列表,请参阅文档。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.