ValueError：检查输入时出错：预期gru_5_input具有形状（无，无，10），但数组的形状为（1、4、1）

Question

我正在尝试使用Python中的TensorFlow和Keras使用循环神经网络进行每小时预测。我已将神经网络的输入分配为{None，None，5），显示在中。

但是，我遇到了错误ː

  

ValueError: Error when checking input: expected gru_3_input to have shape (None, None, 10) but got array with shape (1, 4, 1)我的MVCE代码是ː

%matplotlib inline
#!pip uninstall keras
#!pip install keras==2.1.2
import tensorflow as tf
import pandas as pd 
from pandas import DataFrame 
import math




#####Create the Recurrent Neural Network###


model = Sequential()


model.add(GRU(units=5, 
                return_sequences=True,
                input_shape=(None, num_x_signals)))

## This line is going to map the above 512 values to just 1 (num_y_signal)
model.add(Dense(num_y_signals, activation='sigmoid'))

if False:
    from tensorflow.python.keras.initializers import RandomUniform

    # Maybe use lower init-ranges.##### I may have to change these during debugging####
    init = RandomUniform(minval=-0.05, maxval=0.05)

    model.add(Dense(num_y_signals,
                    activation='linear',
                    kernel_initializer=init))

warmup_steps = 5

def loss_mse_warmup(y_true, y_pred):

    #
    # Ignore the "warmup" parts of the sequences
    # by taking slices of the tensors.
    y_true_slice = y_true[:, warmup_steps:, :]
    y_pred_slice = y_pred[:, warmup_steps:, :]

    # These sliced tensors both have this shape:
    # [batch_size, sequence_length - warmup_steps, num_y_signals]

    # Calculate the MSE loss for each value in these tensors.
    # This outputs a 3-rank tensor of the same shape.
    loss = tf.losses.mean_squared_error(labels=y_true_slice,
                                        predictions=y_pred_slice)



    loss_mean = tf.reduce_mean(loss)

    return loss_mean

optimizer = RMSprop(lr=1e-3) ### This is somthing related to debugging 



model.compile(loss=loss_mse_warmup, optimizer=optimizer)#### I may have to make the output a singnal rather than the whole data set 

print(model.summary())


model.fit_generator(generator=generator,
                    epochs=20,
                    steps_per_epoch=100,
                    validation_data=validation_data)

我不确定为什么会这样，但是我相信这可能与重塑我的训练和测试数据有关。 ɪ还将我完整的错误消息附加到我的代码中，以使问题可重现。

Answer 1

我不确定正确性，但这是：

%matplotlib inline
#!pip uninstall keras
#!pip install keras==2.1.2
import tensorflow as tf
import pandas as pd 
from pandas import DataFrame 
import math
import numpy 
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
import datetime
from keras.layers import Input, Dense, GRU, Embedding
from keras.optimizers import RMSprop
from keras.callbacks import EarlyStopping, ModelCheckpoint, TensorBoard, ReduceLROnPlateau


datetime = [datetime.datetime(2012, 1, 1, 1, 0, 0) + datetime.timedelta(hours=i) for i in range(10)]




X=np.array([2.25226244,1.44078451,0.99174488,0.71179491,0.92824542,1.67776948,2.96399534,5.06257161,7.06504245,7.77817664
               ,0.92824542,1.67776948,2.96399534,5.06257161,7.06504245,7.77817664])

y= np.array([0.02062136,0.00186715,0.01517354,0.0129046 ,0.02231125,0.01492537,0.09646542,0.28444476,0.46289928,0.77817664
                ,0.02231125,0.01492537,0.09646542,0.28444476,0.46289928,0.77817664])

X = X[1:11]
y= y[1:11]

df = pd.DataFrame({'date':datetime,'y':y,'X':X})



df['t']= [x for x in range(10)]
df['X-1'] = df['X'].shift(-1)


x_data = df['X-1'].fillna(0)

y_data = y 

num_data = len(x_data) 

    #### training and testing split####
train_split = 0.6
num_train = int(train_split*num_data)   
num_test = num_data-num_train## number of observations in test set


    #input train test 
x_train = x_data[0:num_train].reshape(-1, 1)
x_test = x_data[num_train:].reshape(-1, 1)
    #print (len(x_train) +len( x_test))

    #output train test 
y_train = y_data[0:num_train].reshape(-1, 1)
y_test = y_data[num_train:].reshape(-1, 1)
    #print (len(y_train) + len(y_test))


    ### number of input signals 
num_x_signals = x_data.shape[0]
   # print (num_x_signals)

    ## number of output signals##

num_y_signals = y_data.shape[0]
    #print (num_y_signals)

    ####data scalling'###

x_scaler = MinMaxScaler(feature_range=(0,1))
x_train_scaled = x_scaler.fit_transform(x_train)



x_test_scaled = MinMaxScaler(feature_range=(0,1)).fit_transform(x_test)

y_scaler = MinMaxScaler()
y_train_scaled = y_scaler.fit_transform(y_train)
y_test_scaled = MinMaxScaler(feature_range=(0,1)).fit_transform(y_test)



def batch_generator(batch_size, sequence_length):
    """
    Generator function for creating random batches of training-data.
    """

    # Infinite loop.  providing the neural network with random data from the 
    # datase for x and y 
    while True:
        # Allocate a new array for the batch of input-signals.
        x_shape = (batch_size, sequence_length, num_x_signals)
        x_batch = np.zeros(shape=x_shape, dtype=np.float16)

        # Allocate a new array for the batch of output-signals.
        y_shape = (batch_size, sequence_length, num_y_signals)
        y_batch = np.zeros(shape=y_shape, dtype=np.float16)

        # Fill the batch with random sequences of data.
        for i in range(batch_size):
            # Get a random start-index.
            # This points somewhere into the training-data.
            idx = np.random.randint(num_train - sequence_length)

            # Copy the sequences of data starting at this index.
            x_batch[i] = x_train_scaled[idx:idx+sequence_length]
            y_batch[i] = y_train_scaled[idx:idx+sequence_length]

        yield (x_batch, y_batch)


batch_size =20




sequence_length = 2 


generator = batch_generator(batch_size=batch_size,
                            sequence_length=sequence_length)

x_batch, y_batch = next(generator)




#########Validation Set Start########

def batch_generator(batch_size, sequence_length):
    """
    Generator function for creating random batches of training-data.
    """

    # Infinite loop.  providing the neural network with random data from the 
    # datase for x and y 
    while True:
        # Allocate a new array for the batch of input-signals.
        x_shape = (batch_size, sequence_length, num_x_signals)
        x_batch = np.zeros(shape=x_shape, dtype=np.float16)

        # Allocate a new array for the batch of output-signals.
        y_shape = (batch_size, sequence_length, num_y_signals)
        y_batch = np.zeros(shape=y_shape, dtype=np.float16)

        # Fill the batch with random sequences of data.
        for i in range(batch_size):
            # Get a random start-index.
            # This points somewhere into the training-data.
            idx = np.random.randint(num_train - sequence_length)

            # Copy the sequences of data starting at this index.
            x_batch[i] = x_test_scaled[idx:idx+sequence_length]
            y_batch[i] = y_test_scaled[idx:idx+sequence_length]

        yield (x_batch, y_batch)
validation_data= next(batch_generator(batch_size,sequence_length))

# validation_data = (np.expand_dims(x_test_scaled, axis=0),
#                     np.expand_dims(y_test_scaled, axis=0))

#Validation set end

#####Create the Recurrent Neural Network###


model = Sequential()


model.add(GRU(units=5, 
                return_sequences=True,
                input_shape=(None, num_x_signals)))

## This line is going to map the above 512 values to just 1 (num_y_signal)
model.add(Dense(num_y_signals, activation='sigmoid'))

if False:
    from tensorflow.python.keras.initializers import RandomUniform

    # Maybe use lower init-ranges.##### I may have to change these during debugging####
    init = RandomUniform(minval=-0.05, maxval=0.05)

    model.add(Dense(num_y_signals,
                    activation='linear',
                    kernel_initializer=init))

warmup_steps = 5

def loss_mse_warmup(y_true, y_pred):

    #
    # Ignore the "warmup" parts of the sequences
    # by taking slices of the tensors.
    y_true_slice = y_true[:, warmup_steps:, :]
    y_pred_slice = y_pred[:, warmup_steps:, :]

    # These sliced tensors both have this shape:
    # [batch_size, sequence_length - warmup_steps, num_y_signals]

    # Calculate the MSE loss for each value in these tensors.
    # This outputs a 3-rank tensor of the same shape.
    loss = tf.losses.mean_squared_error(labels=y_true_slice,
                                        predictions=y_pred_slice)



    loss_mean = tf.reduce_mean(loss)

    return loss_mean

optimizer = RMSprop(lr=1e-3) ### This is somthing related to debugging 



model.compile(loss=loss_mse_warmup, optimizer=optimizer)#### I may have to make the output a singnal rather than the whole data set 

print(model.summary())


model.fit_generator(generator=generator,
                    epochs=20,
                    steps_per_epoch=100,
                    validation_data=validation_data)

我只更改了validation set start和validation set end之间的部分代码。