1樓:busy
你試試:
from
keras.layers
import
Layer
,Input
from
keras
import
backendasK
from
keras.models
import
Model
class
CustLayer
(Layer
):def
__init__
(self,**
kwargs
):super
(CustLayer
,self).
__init__(**
kwargs
)def
build
(self
,input_shape
):self.w
=self
.add_weight
(name
='weights'
,shape=(
len(
input_shape),1
),initializer
='uniform'
,trainable
=True
)def
call
(self
,inputs,**
kwargs
):returnK.
dot(K.
stack
(inputs
,axis=-1
),self.w
)[...,-
1]a=
Input((7
,3))b
=Input((7
,3))c
=Input((7
,3))d
=Input((7
,3))output
=CustLayer
()([a,
b,c,
d])model
=Model([a
,b,c
,d],output
(model
.output
.shape)
2樓:
class
WeightedSum
(Layer
):def
__init__
(self,a
,**kwargs
):self.a
=asuper
(WeightedSum
,self).
__init__(**
kwargs
)def
call
(self
,model_outputs
):return
self.a
*model_outputs[0
]+(1
-self.a
)*model_outputs[1
]def
compute_output_shape
(self
,input_shape
):return
input_shape[0
]# Create model1
inp1
=Input((5
,))#d1 = Dense(100)(inp1)#out1 = Dense(10)(d1)#model1 = Model(inp1, out1)# Create model2
inp2
=Input((7
,))#d2 = Dense(70)(inp2)#out2 = Dense(10)(d2)#model2 = Model(inp2, out2)# Weighed sum of the two models' outputs with a = 0.1
out=
WeightedSum
(0.1
)([inp1
,inp2
])# extend this part in your case# Create the merged modelmodel
=Model
(inputs=[
inp1
,inp2
],outputs=[
out])
keras中如何呼叫autoencoder?
年豆兒 貼個keras自己的autoencoder部落格教程 blog.keras.io building autoencoders in keras.html還有個中文版翻譯的 Keras與各種各樣的自編碼器 Young Well 提了問題後不久問題解決了,一直也忘了來回答,ling wei說的是...
hbase中過濾器如何多個使用?
IT野狐禪 定義過濾器鏈 FilterList filterList newFilterList FilterList.Operator.MUST PASS ALL 分頁過濾器 Filter filter2 newPageFilter 2 Rowfilter Filter filter1 newRo...
如何在 DAG 中找多個點的 LCA
阮行止 如果允許離線,整個問題可以做到 的複雜度。先考慮這個問題在樹上的版本。還用這個問題出了一道胡策 HNSDFZ 7 捂臉 這是題面 這是題解 先說結論 樹上多個點的LCA,就是DFS序最小的和DFS序最大的這兩個點的LCA。例如,在下圖的樹中,2,4,6,7 的LCA就是 2,7 的LCA。以...