Question

我在宣布我的模型时遇到了问题。我的输入是x_input和y_input，我的输出是预测。如下：

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

我的输入（x，y）都嵌入了，然后是MatMult。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

同样适用于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

然后我在两者之间做了一个批处理。（只需点击每个实例的数据）

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)`

然后我压扁了张量的最后两个维度。

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

最终，我将这些扁平数据反馈到一个简单的逻辑回归器中。

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

而且，我的预测当然是我对模型的输出。

我将按张量的输出形状列出每层的输出。

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)

具体来说，我得到以下错误。

    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。我哪里做错了？谢谢你提前帮忙！

- 安东尼

Answer 1

您是否尝试将后端功能包装到__call__()图层中？我认为在Keras层的Model方法中有一些必要的操作可以正确构建Keras class Migration(migrations.Migration): dependencies = [ ('projects', '0001_initial'), ]，如果直接调用后端函数则不会执行。

Keras后端建模问题

1 个答案: