AttributeError: 'Model' object has no attribute 'name'

Question

I am new to Keras and I was trying to build a text-classification CNN model using Python 3.6 when I encountered this error :

AttributeError: 'Model' object has no attribute 'name'

This is the code that I have written :

print("\nCreating Model...")
x1 = Input(shape=(seq_len1, 100), name='x1')
x2 = Input(shape=(seq_len2, 100), name='x2')
x1 = Reshape((seq_len1, embedding_dim, 1))(x1)
x2 = Reshape((seq_len2, embedding_dim, 1))(x2)

conv_0 = Conv2D(num_filters, kernel_size=(filter_sizes[0], 1), padding='valid', kernel_initializer='normal', activation='relu')
conv_1 = Conv2D(num_filters, kernel_size=(filter_sizes[1], 1), padding='valid', kernel_initializer='normal', activation='relu')
conv_2 = Conv2D(num_filters, kernel_size=(filter_sizes[2], 1), padding='valid', kernel_initializer='normal', activation='relu')

maxpool = MaxPool2D(pool_size=(2, 1), strides=(1,1), padding='valid')

output1 = conv_0(x1)
output1 = maxpool(output1)
output1 = conv_1(output1)
output1 = maxpool(output1)
output1 = conv_2(output1)
output1 = maxpool(output1)
.
.
# Same for output2
.
concatenated_tensor = Concatenate(axis=1)([output1, output2])
flatten = Flatten()(concatenated_tensor)
#dropout = Dropout(drop)(flatten)
output = Dense(units=1024, activation='relu')(flatten)
output = Dense(units=1024, activation='relu')(output)
output = Dense(units=1, activation='softmax')(output)

# this creates a model that includes
model = Model(inputs=[x1, x2], outputs=[output])

The error is encountered at last line. Please help me resolve this

EDIT :

Traceback (most recent call last):
  File "model.py", line 91, in <module>
    model = Model(inputs=[x1, x2], outputs=[out])
  File "/../../anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/network.py", line 91, in __init__
    self._init_graph_network(*args, **kwargs)
  File "/../../anaconda3/lib/python3.6/site-packages/keras/engine/network.py", line 183, in _init_graph_network
    'The tensor that caused the issue was: ' +
AttributeError: 'Model' object has no attribute 'name'

Can you add the trace, when does your code try to access the name? If you don't specify name argument it will not be set. — nuric
– nuric, Commented Jul 9, 2018 at 20:43
The trace doesn't look complete, are you sure you copied it correctly? — Dr. Snoopy
– Dr. Snoopy, Commented Jul 9, 2018 at 20:55

Abhishek Sehgal · Accepted Answer · 2018-07-09 20:48:13Z

18

x1 and x2 point to the Reshape layers for the input and not the Input layers themselves.

answered Jul 9, 2018 at 20:48

Abhishek Sehgal

6085 silver badges16 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

code-freeze · Accepted Answer · 2020-08-07 07:39:51Z

0

The same error popped up for me when i used custom "swish" activation function. I could resolve the same , with this code

class Swish(Activation):
    def __init__(self, activation, **kwargs):
        super(Swish, self).__init__(activation, **kwargs)
        self.__name__ = 'swish'
def swish(x,beta=1):
    return (x*sigmoid(x*beta))
get_custom_objects().update({'swish': Swish(swish)})

answered Aug 7, 2020 at 7:39

code-freeze

4958 silver badges9 bronze badges

Collectives™ on Stack Overflow

AttributeError: 'Model' object has no attribute 'name'

2 Answers 2

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related