Keras後端造型發出

Question

我有我的聲明模型的問題。我的輸入是x_input和y_input，我的輸出是預測。如下：

model = Model(inputs = [x_input, y_input], outputs = predictions) 

我的輸入（X，Y）都嵌入，然後MatMult在一起。具體如下：

# Build X Branch 
x_input = Input(shape = (maxlen_x,), dtype = 'int32')        
x_embed = Embedding(maxvocab_x + 1, 16, input_length = maxlen_x) 
XE = x_embed(x_input) 
# Result: Tensor("embedding_1/Gather:0", shape=(?, 31, 16), dtype=float32) 
# Where 31 happens to be my maxlen_x 

同樣對Y分支...

# Build Y Branch 
y_input = Input(shape = (maxlen_y,), dtype = 'int32')        
y_embed = Embedding(maxvocab_y + 1, 16, input_length = maxlen_y) 
YE = y_embed(y_input) 
# Result: Tensor("embedding_1/Gather:0", shape=(?, 13, 16), dtype=float32) 
# Where 13 happens to be my maxlen_y 

我然後做兩者之間的批點。 （只需點擊每個實例的數據）

from keras import backend as K 
dot_merged = K.batch_dot(XE, YE, axes=[2,2]) # Choose the 2nd component of both inputs to Dot, using batch_dot 
# Result: Tensor("MatMul:0", shape=(?, 31, 13), dtype=float32)` 

然後，我將張量的最後兩個維度展平。

dim = np.prod(list(dot_merged.shape)[1:]) 
flattened= K.reshape(dot_merged, (-1,int(dim))) 

最終，我把這個扁平數據放入一個簡單的邏輯迴歸器。

predictions = Dense(1,activation='sigmoid')(flattened) 

而且，我的預測當然是我的模型輸出。

我將由張量的輸出形狀列出每個層的輸出。

Tensor("embedding_1/Gather:0", shape=(?, 31, 16), dtype=float32) 
Tensor("embedding_2/Gather:0", shape=(?, 13, 16), dtype=float32) 
Tensor("MatMul:0", shape=(?, 31, 13), dtype=float32) 
Tensor("Reshape:0", shape=(?, 403), dtype=float32) 
Tensor("dense_1/Sigmoid:0", shape=(?, 1), dtype=float32) 

我收到以下錯誤，具體是。

Traceback (most recent call last): 
    File "Model.py", line 53, in <module> 
    model = Model(inputs = [dx_input, rx_input], outputs = [predictions]) 
    File "/Users/jiangq/tensorflow/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 88, in wrapper 
    return func(*args, **kwargs) 
    File "/Users/jiangq/tensorflow/lib/python3.6/site-packages/keras/engine/topology.py", line 1705, in __init__ 
    build_map_of_graph(x, finished_nodes, nodes_in_progress) 
    File "/Users/jiangq/tensorflow/lib/python3.6/site-packages/keras/engine/topology.py", line 1695, in build_map_of_graph 
    layer, node_index, tensor_index) 
    File "/Users/jiangq/tensorflow/lib/python3.6/site-packages/keras/engine/topology.py", line 1665, in build_map_of_graph 
    layer, node_index, tensor_index = tensor._keras_history 
AttributeError: 'Tensor' object has no attribute '_keras_history' 

Volia。我哪裏做錯了？ 感謝您提前提供幫助！

- 安東尼

Answer 1

你有沒有試過包裝後端功能集成到一個Lambda層？ 我覺得有一個Keras層的__call__()方法中的一些必要的操作的Keras Model要正確建立，如果直接調用後端功能，這將不會被執行。