Python 如何在 keras 中使用 lambda 层？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/44886195/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How to use lambda layer in keras?
提问by Ting Li
I want to define lambda layer to combine features with cross product, then merge those models,just like the fig. ,What should I do?
我想定义 lambda 层以将特征与叉积相结合，然后合并这些模型，就像图一样。，我该怎么办？
Test model_1, get 128 dimensions form dense, use pywtget two 64 dimensions feature(cA,cD), then return cA*cD //of course I want to combine two models ,but try model_1 first.
测试model_1，得到128维形成dense，使用pywt得到两个64维的feature( cA,cD)，然后返回cA*cD //当然我想合并两个模型，但是先试试model_1。
from keras.models import Sequential,Model
from keras.layers import Input,Convolution2D,MaxPooling2D
from keras.layers.core import Dense,Dropout,Activation,Flatten,Lambda
import pywt
def myFunc(x):
(cA, cD) = pywt.dwt(x, 'db1')
# x=x*x
return cA*cD
batch_size=32
nb_classes=3
nb_epoch=20
img_rows,img_cols=200,200
img_channels=1
nb_filters=32
nb_pool=2
nb_conv=3
inputs=Input(shape=(1,img_rows,img_cols))
x=Convolution2D(nb_filters,nb_conv,nb_conv,border_mode='valid',
input_shape=(1,img_rows,img_cols),activation='relu')(inputs)
x=Convolution2D(nb_filters,nb_conv,nb_conv,activation='relu')(x)
x=MaxPooling2D(pool_size=(nb_pool,nb_pool))(x)
x=Dropout(0.25)(x)
x=Flatten()(x)
y=Dense(128,activation='relu')(x)
cross=Lambda(myFunc,output_shape=(64,))(y)
predictions=Dense(nb_classes,activation='softmax')(cross)
model = Model(input=inputs, output=predictions)
model.compile(loss='categorical_crossentropy',optimizer='adadelta',metrics=['accuracy'])
model.fit(X_train,Y_train,batch_size=batch_size,nb_epoch=nb_epoch,
verbose=1,validation_data=(X_test,Y_test))
Sorry, can I ask a question about tensor?
抱歉，我可以问一个关于张量的问题吗？
import tensorflow as tf
W1 = tf.Variable(np.array([[1,2],[3,4]]))
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
array = W1.eval(sess)
print (array)
That's right! However,
这是正确的！然而，
from keras import backend as K
import numpy as np
kvar=K.variable(np.array([[1,2],[3,4]]))
K.eval(kvar)
print(kvar)
I got <CudaNdarrayType(float32, matrix)>and kvar.eval()I got b'CudaNdarray([[ 1. 2.]\n [ 3. 4.]])'. I use keras, so how can I get array like tensorflow using keras?
我得到了<CudaNdarrayType(float32, matrix)>，kvar.eval()我得到了b'CudaNdarray([[ 1. 2.]\n [ 3. 4.]])'。我使用 keras，那么如何使用 keras 获得像 tensorflow 这样的数组？
采纳答案by Daniel M?ller
I would probaly duplicate the dense layers. Instead of having 2 layers with 128 units, have 4 layers with 64 units. The result is the same, but you will be able to perform the cross products better.
我可能会复制密集层。不是有 2 层有 128 个单元，而是有 4 层有 64 个单元。结果是相同的，但您将能够更好地执行交叉产品。
from keras.models import Model
#create dense layers and store their output tensors, they use the output of models 1 and to as input
d1 = Dense(64, ....)(Model_1.output)
d2 = Dense(64, ....)(Model_1.output)
d3 = Dense(64, ....)(Model_2.output)
d4 = Dense(64, ....)(Model_2.output)
cross1 = Lambda(myFunc, output_shape=....)([d1,d4])
cross2 = Lambda(myFunc, output_shape=....)([d2,d3])
#I don't really know what kind of "merge" you want, so I used concatenate, there are Add, Multiply and others....
output = Concatenate()([cross1,cross2])
#use the "axis" attribute of the concatenate layer to define better which axis will be doubled due to the concatenation
model = Model([Model_1.input,Model_2.input], output)
Now, for the lambda function:
现在，对于 lambda 函数：
import keras.backend as K
def myFunc(x):
return x[0] * x[1]
