Keras神经网络断言错误

我有一个Keras断言错误麻烦，想问一下，如果任何人都可以请帮助：Keras神经网络断言错误

我已经跑Keras NN之前，二维卷积从来没见过这个错误。

#-----------------BEGIN FUNCTION 1----------------- 
def create_model(input_size1, num_labels, conv1_num_filters, conv1_filter_size1, conv2_num_filters, conv2_filter_size1, pool1_1, dropout1, pool2_1, dropout2, neurons1, reg_l2, neurons2, reg_l2_2): 

    model = Sequential() 
    model.add(Convolution1D(conv1_num_filters, conv1_filter_size1, init = 'glorot_uniform', border_mode='same', 
     input_shape=(1, input_size1), 
     activation = 'relu')) 
    model.add(MaxPooling1D(pool_length=(pool1_1),border_mode='same')) 
    model.add(BatchNormalization(epsilon=0.001, mode=0, axis=1, momentum=0.99, weights=None, beta_init='zero', gamma_init='one', gamma_regularizer=None, beta_regularizer=None)) 
    model.add(Convolution1D(conv2_num_filters, conv2_filter_size1, init = 'glorot_uniform', activation = 'relu', border_mode='same')) 
    model.add(MaxPooling1D(pool_length=(pool1_1),border_mode='same')) 
    model.add(Dropout(dropout1)) 
    model.add(Flatten()) 
    model.add(BatchNormalization(epsilon=0.001, mode=0, axis=1, momentum=0.99, weights=None, beta_init='zero', gamma_init='one', gamma_regularizer=None, beta_regularizer=None)) 
    model.add(Dense(neurons1, W_regularizer=l2(reg_l2), init = 'glorot_uniform', activation = 'relu')) 
    model.add(Dropout(dropout2)) 
    model.add(BatchNormalization(epsilon=0.001, mode=0, axis=1, momentum=0.99, weights=None, beta_init='zero', gamma_init='one', gamma_regularizer=None, beta_regularizer=None)) 
    model.add(Dense(neurons2, W_regularizer=l2(reg_l2_2), init = 'glorot_uniform', activation = 'relu')) 
    model.add(Dense(num_labels, init = 'glorot_uniform', activation = 'tanh')) 

    sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) #0.01 
    model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) 

    print(model.summary()) 
    #exit() 

    return model 
#-----------------END FUNCTION 1----------------- 

model2 = create_model(input_size1, num_labels, conv1_num_filters, 
         conv1_filter_size1, conv2_num_filters, 
         conv2_filter_size1, pool1_1, dropout1, pool2_1, 
         dropout2, neurons1, reg_l2, neurons2, reg_l2_2); 

x_train_ex = np.expand_dims(x_train, 1) 
x_test_ex = np.expand_dims(x_test, 1) 

from keras.utils.np_utils import to_categorical 
y_train_ex = to_categorical(y_train, len(np.unique(y_train))) 
y_test_ex = to_categorical(y_test, len(np.unique(y_train))) 

model2.fit(x_train_ex, y_train_ex, batch_size=batch_size, nb_epoch=nb_epoch, 
      verbose=1, validation_data=(x_test_ex, y_test_ex)

）

我得到一个错误说：

--------------------------------------------------------------------------- 
AssertionError       Traceback (most recent call last) 
<ipython-input-41-c4780c441db5> in <module>() 
    26 
    27 model2.fit(x_train_ex, y_train_ex, batch_size=batch_size, nb_epoch=nb_epoch, 
---> 28   verbose=1, validation_data=(x_test_ex, y_test_ex)) 
    29 #print(model2.score(x_train_ex, y_train)) 
    30 #print(model2.score(x_test_ex, y_test)) 

.........(Lots more error messages) 


AssertionError:

非常感谢您！

来源

2017-02-19 Scott Yiu

不要编辑错误消息，将它们全部粘贴。 –

对不起，今后会做。 –

当我从Keras 1.1.1升级到1.2.0时，问题似乎消失了。可能是版本问题。

来源

2017-02-20 12:00:51

Keras神经网络断言错误

回答

相关问题