Question

定义虚拟对象

from keras.layers import Input, Dense
from keras.models import Model
import keras

inputs = Input(shape=(100,), name='A_input')
x = Dense(20, activation='relu', name='B_dense')(inputs)
shared_l = Dense(20, activation='relu', name='C_dense_shared')
x = keras.layers.concatenate([shared_l(x), shared_l(x)], name='D_concat')

model = Model(inputs=inputs, outputs=x)
print(model.summary())

产生以下输出

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
A_input (InputLayer)             (None, 100)           0                                            
____________________________________________________________________________________________________
B_dense (Dense)                  (None, 20)            2020        A_input[0][0]                    
____________________________________________________________________________________________________
C_dense_shared (Dense)           (None, 20)            420         B_dense[0][0]                    
                                                                   B_dense[0][0]                    
____________________________________________________________________________________________________
D_concat (Concatenate)           (None, 40)            0           C_dense_shared[0][0]             
                                                                   C_dense_shared[1][0]             
====================================================================================================

我的问题涉及Connected to列的内容。我理解a layer can have multiple nodes。

在这种情况下，C_dense_shared有两个节点，D_concat连接到它们（C_dense_shared[0][0]和C_dense_shared[1][0]）。所以第一个索引（node_index）对我来说很清楚。但第二个指数意味着什么？从source code我读到这是tensor_index：

layer_name[node_index][tensor_index]

但tensor_index是什么意思？在什么情况下，它的值可能与0不同？

Answer 1

我认为Node类的docstring非常明确：

    tensor_indices: a list of integers,
        the same length as `inbound_layers`.
        `tensor_indices[i]` is the index of `input_tensors[i]` within the
        output of the inbound layer
        (necessary since each inbound layer might
        have multiple tensor outputs, with each one being
        independently manipulable).

如果图层具有多个输出张量，则

tensor_index将为非零值。它与多个“数据流”（例如图层共享）的情况不同，其中图层具有多个出站节点。例如，LSTM图层将返回3个张量，如果给定return_state=True：

上一个时间步的隐藏状态，或return_sequences=True
最后一步的隐藏状态
最后一步的记忆细胞

另一个例子是，功能转换可以实现为Lambda层：

def generate_powers(x):
    return [x, K.sqrt(x), K.square(x)]

model_input = Input(shape=(10,))
powers = Lambda(generate_powers)(model_input)
x = Concatenate()(powers)
x = Dense(10, activation='relu')(x)
x = Dense(1, activation='sigmoid')(x)
model = Model(model_input, x)

从model.summary()，您可以看到concatenate_5已与lambda_7[0][0]，lambda_7[0][1]和lambda_7[0][2]相关联：

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_7 (InputLayer)             (None, 10)            0                                            
____________________________________________________________________________________________________
lambda_7 (Lambda)                [(None, 10), (None, 1 0           input_7[0][0]                    
____________________________________________________________________________________________________
concatenate_5 (Concatenate)      (None, 30)            0           lambda_7[0][0]                   
                                                                   lambda_7[0][1]                   
                                                                   lambda_7[0][2]                   
____________________________________________________________________________________________________
dense_8 (Dense)                  (None, 10)            310         concatenate_5[0][0]              
____________________________________________________________________________________________________
dense_9 (Dense)                  (None, 1)             11          dense_8[0][0]                    
====================================================================================================
Total params: 321 
Trainable params: 321 
Non-trainable params: 0
____________________________________________________________________________________________________

理解Keras模型架构（张量指数）

1 个答案: