Список Numpy массивов, передаваемых модели, не соответствует ожидаемому размеру модели.

Question

Я не могу решить эту ошибку. Кто-нибудь может решить эту ошибку? Я буду очень благодарен заранее.

Ниже я приложил свой код и ошибку этого кода:

ValueError                                Traceback (most recent call last)
<ipython-input-65-ec0e93dabcc7> in <module>
     82 # hist = model.fit(X_train, y_train, batch_size=58, nb_epoch=10, validation_split = 0.1, verbose = 1)
     83 hist=model.fit(X_train,y_train,batch_size=128,epochs=10,
---> 84 validation_split=0.2,callbacks=[EarlyStopping(monitor='val_loss',min_delta=0.0001)])
     85 
     86 score, acc = model.evaluate(X_test, y_test, batch_size=1)

~\Anaconda3\lib\site-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, steps_per_epoch, validation_steps, **kwargs)
    950             sample_weight=sample_weight,
    951             class_weight=class_weight,
--> 952             batch_size=batch_size)
    953         # Prepare validation data.
    954         do_validation = False

~\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    749             feed_input_shapes,
    750             check_batch_axis=False,  # Don't enforce the batch size.
--> 751             exception_prefix='input')
    752 
    753         if y is not None:

~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    100                 'Expected to see ' + str(len(names)) + ' array(s), '
    101                 'but instead got the following list of ' +
--> 102                 str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
    103         elif len(names) > 1:
    104             raise ValueError(

ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 58 arrays: [array([[5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5.80e+17],
       [5...

Основная ошибка

Список Numpy массивы, передаваемые в модель, не соответствуют ожидаемой модели

Я приложил снимок экрана с кодом, вызывающим ошибку: https://i.stack.imgur.com/MdGN7.png

Answer 1

def load_data(test_split = 0.5):
    print ('Loading data...')
    df = pd.read_csv(input_file)
   # df['sequence'] = df['sequence'].apply(lambda x: [int(e) for e in x.split()])
   #df = df.reindex(np.random.permutation(df.index))

 #   train_size = int(len(df) * (1 - test_split))

#     X_train = df['symbol_count'].values[:train_size]
#     y_train = np.array(df['is_rumor'].values[:train_size])
#     X_test = np.array(df['symbol_count'].values[train_size:])
#     y_test = np.array(df['is_rumor'].values[train_size:])

    y = df['is_rumor']
    X = df.drop("is_rumor",axis = 1)
    xTrain, xTest, yTrain, yTest = test_train_split(X,y)

#     print("X_Train")
#     print(xTrain.head())
#     print("X_Test")
#     print(xTest.head())
#     print("Y_Train")
#     print(yTrain.head())
#     print("y_Test")
#     print(yTest.head())


    xTrain = xTrain.values.tolist()
    xTest = xTest.values.tolist()
    yTrain = yTrain.values.tolist()
    yTest = yTest.values.tolist()


    return xTrain, yTrain, xTest, yTest
   # return pad_sequences(X_train), y_train, pad_sequences(X_test), y_test
def load_my_data():
    print ('Loading data...')
    df = pd.read_csv(input_file)
    y = df['is_rumor']
    X = df.drop("is_rumor",axis = 1)
    xTrain, xTest, yTrain, yTest = test_train_split(X,y)
    x_train = []
    for i in xTrain:
        one_feature = df[i]
        x_train.append(one_feature)
    return x_train, yTrain, xTest, yTest

def create_model(input_length):
    print ('Creating model...')
    model = Sequential()
    model.add(Embedding(input_dim = 188, output_dim = 50, input_length = input_length))
    model.add(LSTM(output_dim=256, activation='sigmoid', inner_activation='hard_sigmoid', return_sequences=True))
    model.add(Dropout(0.5))
    model.add(LSTM(output_dim=256, activation='sigmoid', inner_activation='hard_sigmoid'))
    model.add(Dropout(0.5))
    model.add(Dense(1, activation='sigmoid'))

    print ('Compiling...')
    model.compile(loss='binary_crossentropy',
                  optimizer='rmsprop',
                  metrics=['accuracy'])
    return model


X_train, y_train, X_test, y_test = load_my_data()

model = create_model(len(X_train[0]))
print("----------------checking--------------------------------------------")

print ('Fitting model...')
# hist = model.fit(X_train, y_train, batch_size=58, nb_epoch=10, validation_split = 0.1, verbose = 1)
hist=model.fit(X_tra`enter code here`in,y_train,batch_size=128,epochs=10,
validation_split=0.2,callbacks=[EarlyStopping(monitor='val_loss',min_delta=0.0001)])

score, acc = model.evaluate(X_test, y_test, batch_size=1)
print('Test score:', score)
print('Test accuracy:', acc)