Skip to main content
 首页 » 编程设计

python之属性错误 : 'Tensor' object has no attribute '_keras_shape' when creating a model in keras

2024年12月31日8yjmyzz

当我在 keras 中定义模型时,错误如下所示 AttributeError: 'Tensor' 对象没有属性 '_keras_shape'

产生错误的代码是

vocab_size = 10000 
MAX_SEQUENCE_LENGTH = 256 
sequence_input = keras.layers.Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32') 
embedding=keras.layers.Embedding(vocab_size, 16, input_length  = MAX_SEQUENCE_LENGTH)(sequence_input) 
x=keras.layers.GlobalAveragePooling1D()(embedding) 
x=keras.layers.Dense(16, activation=tf.nn.relu)(x) 
 
preds = keras.layers.Dense(1, activation=tf.nn.sigmoid)(x) 
 
model = Model(inputs=sequence_input, outputs=preds) 
model.compile(optimizer=tf.train.AdamOptimizer(), 
          loss='binary_crossentropy', 
          metrics=['accuracy']) 

完整的错误信息如下所示

AttributeError                            Traceback (most recent call last) 
<ipython-input-5-1c6ea41c38e1> in <module>() 
      1 from keras.models import Model 
----> 2 model = Model(inputs=sequence_input, outputs=preds) 
      3 model.compile(optimizer=tf.train.AdamOptimizer(), 
      4               loss='binary_crossentropy', 
      5               metrics=['accuracy']) 
 
~/Datacube/datacube_env/lib/python3.5/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs) 
     89                 warnings.warn('Update your `' + object_name + 
     90                               '` call to the Keras 2 API: ' + signature, stacklevel=2) 
---> 91             return func(*args, **kwargs) 
     92         wrapper._original_function = func 
     93         return wrapper 
 
~/Datacube/datacube_env/lib/python3.5/site-packages/keras/engine/network.py in __init__(self, *args, **kwargs) 
     89                 'inputs' in kwargs and 'outputs' in kwargs): 
     90             # Graph network 
---> 91             self._init_graph_network(*args, **kwargs) 
     92         else: 
     93             # Subclassed network 
 
~/Datacube/datacube_env/lib/python3.5/site-packages/keras/engine/network.py in _init_graph_network(self, inputs, outputs, name) 
    249              input_masks=[None for _ in self.inputs], 
    250              output_masks=[None for _ in self.outputs], 
--> 251              input_shapes=[x._keras_shape for x in self.inputs], 
    252              output_shapes=[x._keras_shape for x in self.outputs]) 
    253  
 
~/Datacube/datacube_env/lib/python3.5/site-packages/keras/engine/network.py in <listcomp>(.0) 
    249              input_masks=[None for _ in self.inputs], 
    250              output_masks=[None for _ in self.outputs], 
--> 251              input_shapes=[x._keras_shape for x in self.inputs], 
    252              output_shapes=[x._keras_shape for x in self.outputs]) 
    253  
 
AttributeError: 'Tensor' object has no attribute '_keras_shape' 

谁能告诉我怎么解决

请您参考如下方法:

我注意到,如果您混淆了常规的 keras 导入和 tensorflow 导入,就会发生这种情况。 避免像这样混合导入:

# Mixed imports, one is regular keras, other is TF's keras 
import keras 
from tensorflow.keras.model import Model 
 
sequence_input = keras.layers.Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32') 
... 
model = Model(inputs=sequence_input, outputs=preds) 

例如,从 TF 导入所有内容:

from tensorflow import keras 
from tensorflow.keras.model import Model 
 
sequence_input = keras.layers.Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32') 
... 
model = Model(inputs=sequence_input, outputs=preds) 

或者只使用 Keras:

import keras 
from keras.model import Model 
 
sequence_input = keras.layers.Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32') 
... 
model = Model(inputs=sequence_input, outputs=preds) 

不能确定这是你问题的根本原因,但这可能对某些人有帮助