Keras: TypeError: run() a obtenu un argument mot-clé inattendu 'kernel_regularizer'

Question

J'utilise tensorflow==1.2.1 et Keras==2.0.6 pour construire un modèle:

input_num = X_norm_keras[:,2:].shape[1] 
model_keras = Sequential() 
model_keras.add(Dense(10, input_dim=input_num, activation='relu')) 
model_keras.add(Dense(1, activation='linear')) 
kernel_regularizer=regularizers.l2(0.2), optimizer='adam') 
model_keras.compile(loss='mean_squared_error', kernel_regularizer=regularizers.l2(0.2), optimizer='adam') 
model_keras.fit(X_norm_train[:,2:], y_norm_train, batch_size=25, epochs=250) 

mais nous avons eu les erreurs suivantes:

Using TensorFlow backend. 
total data points = (25, 106) 
Epoch 1/250 
--------------------------------------------------------------------------- 
TypeError         Traceback (most recent call last) 
<ipython-input-4-4cbd897903e7> in <module>() 

    102  model_keras.compile(loss='mean_squared_error', kernel_regularizer=regularizers.l2(0.2), optimizer='adam') 
--> 103  model_keras.fit(X_norm_train[:,2:], y_norm_train, batch_size=25, epochs=250) 

/usr/local/lib/python3.4/dist-packages/keras/models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs) 
    861        class_weight=class_weight, 
    862        sample_weight=sample_weight, 
--> 863        initial_epoch=initial_epoch) 
    864 
    865  def evaluate(self, x, y, batch_size=32, verbose=1, 

/usr/local/lib/python3.4/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs) 
    1428        val_f=val_f, val_ins=val_ins, shuffle=shuffle, 
    1429        callback_metrics=callback_metrics, 
-> 1430        initial_epoch=initial_epoch) 
    1431 
    1432  def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None): 

/usr/local/lib/python3.4/dist-packages/keras/engine/training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch) 
    1077     batch_logs['size'] = len(batch_ids) 
    1078     callbacks.on_batch_begin(batch_index, batch_logs) 
-> 1079     outs = f(ins_batch) 
    1080     if not isinstance(outs, list): 
    1081      outs = [outs] 

/usr/local/lib/python3.4/dist-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs) 
    2266   updated = session.run(self.outputs + [self.updates_op], 
    2267        feed_dict=feed_dict, 
-> 2268        **self.session_kwargs) 
    2269   return updated[:len(self.outputs)] 
    2270 

TypeError: run() got an unexpected keyword argument 'kernel_regularizer' 

Am Je manque quelque chose ici? Merci!

Answer 1

Le régularisateur kernel_regularizer=regularizers.l2(0.2) doit être un argument de Dense(), et non de model.compile().

la documentation De model.compile():

**kwargs: When using the Theano/CNTK backends, these arguments are passed into K.function. When using the TensorFlow backend, these arguments are passed into tf.Session.run.

C'est la raison pour laquelle vous voyez une erreur provenant de run().