Concatenate Layer Errors

Question

I am using keras 2.02 and tensorflow 1.3 to build a convolution net with multiple sizes of filters. The code is shown below.

flts=100
kernel_sizes=[2,3,4]
submodels = []
for kw in kernel_sizes:    # kernel sizes
    submodel = Sequential()
    submodel.add(embedding_layer)
    submodel.add(Dropout(0.2))
    submodel.add(Conv1D(filters=flts,
                        kernel_size=kw,
                        padding='same',
                        activation='relu'))
    submodel.add(MaxPooling1D(pool_size=kw))
    submodels.append(submodel)

big_model = Sequential()
#concat = Concatenate(axis=1)     #line B
#big_model.add(concat(submodels)) #line C
big_model.add(Merge(submodels, mode="concat", concat_axis=1))  #line A
big_model.add(LSTM(units=100, return_sequences=True))
big_model.add(GlobalMaxPooling1D())
#big_model.add(Dropout(0.2))
big_model.add(Dense(2, activation='softmax'))
big_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

When using the deprecated code as on line A, it works ok. But when this is replaced by lines B,C, an error is generated as below:

--> 141     big_model.add(concat(submodels))
        big_model.add = <bound method Sequential.add of <keras.models.Sequential object>>
        concat = <keras.layers.merge.Concatenate object>
        submodels = [<keras.models.Sequential object>, <keras.models.Sequential object>, <keras.models.Sequential object>]
    142     big_model.add(LSTM(units=100, return_sequences=True))
    143     big_model.add(GlobalMaxPooling1D())
    144     #big_model.add(Dropout(0.2))
    145     big_model.add(Dense(2, activation='softmax'))


........

/home/zqz/Programs/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in int_shape(x=<keras.models.Sequential object>)
    404         (2, 2)
    405     ```
    406     """
    407     if hasattr(x, '_keras_shape'):
    408         return x._keras_shape
--> 409     shape = x.get_shape()
        shape = undefined
        x.get_shape = undefined
    410     try:
    411         return tuple([i.__int__() for i in shape])
    412     except ValueError:
    413         return None

AttributeError: 'Sequential' object has no attribute 'get_shape'
___________________________________________________________________

I don't know what I should do to fix this?

Thanks in advance

Yu-Yang · Accepted Answer · 2017-11-17 15:20:45Z

I'll suggest using the functional API when your model contains branches. The Concatenate layer takes a list of tensors as its input. In this case, the list should contain the output tensors of the submodels.

submodel_outputs = [model.output for model in submodels]
x = Concatenate(axis=1)(submodel_outputs)

x = LSTM(units=100, return_sequences=True)(x)
x = GlobalMaxPooling1D()(x)
x = Dropout(0.2)(x)
x = Dense(2, activation='softmax')(x)

big_model = Model(inputs=embedding_layer.input, outputs=x)
big_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
big_model.summary()

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to
==================================================================================================
embedding_1_input (InputLayer)  (None, None)         0
__________________________________________________________________________________________________
embedding_1 (Embedding)         (None, None, 64)     64000       embedding_1_input[0][0]
__________________________________________________________________________________________________
dropout_3 (Dropout)             (None, None, 64)     0           embedding_1[0][0]
__________________________________________________________________________________________________
dropout_4 (Dropout)             (None, None, 64)     0           embedding_1[0][0]
__________________________________________________________________________________________________
dropout_5 (Dropout)             (None, None, 64)     0           embedding_1[0][0]
__________________________________________________________________________________________________
conv1d_4 (Conv1D)               (None, None, 100)    12900       dropout_3[0][0]
__________________________________________________________________________________________________
conv1d_5 (Conv1D)               (None, None, 100)    19300       dropout_4[0][0]
__________________________________________________________________________________________________
conv1d_6 (Conv1D)               (None, None, 100)    25700       dropout_5[0][0]
__________________________________________________________________________________________________
max_pooling1d_4 (MaxPooling1D)  (None, None, 100)    0           conv1d_4[0][0]
__________________________________________________________________________________________________
max_pooling1d_5 (MaxPooling1D)  (None, None, 100)    0           conv1d_5[0][0]
__________________________________________________________________________________________________
max_pooling1d_6 (MaxPooling1D)  (None, None, 100)    0           conv1d_6[0][0]
__________________________________________________________________________________________________
concatenate_7 (Concatenate)     (None, None, 100)    0           max_pooling1d_4[0][0]
                                                                 max_pooling1d_5[0][0]
                                                                 max_pooling1d_6[0][0]
__________________________________________________________________________________________________
lstm_4 (LSTM)                   (None, None, 100)    80400       concatenate_7[0][0]
__________________________________________________________________________________________________
global_max_pooling1d_4 (GlobalM (None, 100)          0           lstm_4[0][0]
__________________________________________________________________________________________________
dropout_7 (Dropout)             (None, 100)          0           global_max_pooling1d_4[0][0]
__________________________________________________________________________________________________
dense_4 (Dense)                 (None, 2)            202         dropout_7[0][0]
==================================================================================================
Total params: 202,502
Trainable params: 202,502
Non-trainable params: 0
__________________________________________________________________________________________________

For using Model with the Scikit-Learn API:

class MyKerasClassifier(KerasClassifier):
    def predict(self, x, **kwargs):
        kwargs = self.filter_sk_params(self.model.predict, kwargs)
        proba = self.model.predict(x, **kwargs)
        if proba.shape[-1] > 1:
            classes = proba.argmax(axis=-1)
        else:
            classes = (proba > 0.5).astype('int32')
        return self.classes_[classes]

Originally in KerasClassifier.predict(), the function predict_classes() is called to obtain the predicted classes. You can override this function and compute the classes from the probabilities to avoid the need of predict_classes().

Thank you, the model builds fine but is there no way I can use with the sequential model? the reason is that the Sequential model seems to be the only one that implements 'predict_classes'. I need to wrap the model in a GridSearchCV object and call 'cross_val_predict' which then will call the 'predict_classes' attribute of the classifier. I can update the code with details if needed. Any suggestions please?
@Ziqi The documentation states that the sklearn wrappers are to be used with "Sequential Keras models (single-input only)". So I think you may need to modify the wrapper a bit for your purpose. See my edit for a possible workaround.
thank you it seems to be working technically as the code is running. but results i got are only predicting one out of two classes - every instance belong to that class. but I wonder if that's the semantics of the network for my specific problem. thanks again

Collectives™ on Stack Overflow

Concatenate Layer Errors

1 Answer 1

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related