Stackedautoencoder算法中有一个错误，ValueError:logits和标签必须具有相同的形状（（无，20）vs（无，1））

Question

当我将堆叠自动编码器应用为特征选择时，出现此错误

ValueError: logits and labels must have the same shape ((None, 20) vs (None, 1))

这是堆叠自动编码器的代码：：

import tensorflow

from tensorflow.keras import layers
from tensorflow.keras import activations
from tensorflow.python.keras.layers import Input, Dense
from tensorflow.python.keras.models import Model
from sklearn.preprocessing import MinMaxScaler


def StackedAutoencoder(x_train, x_test, y_train, y_test):
    scalar = MinMaxScaler()
    x_train = scalar.fit_transform(x_train)
    x_test = scalar.fit_transform(x_test)

    input_size = x_train.shape[1]
    hidden_size = 9
    code_size = 3

    input_data = Input(shape=(input_size,))
    hidden_1 = Dense(hidden_size, activation='relu')(input_data)
    code = Dense(code_size, activation='relu')(hidden_1)
    hidden_2 = Dense(hidden_size, activation='relu')(code)
    # decode
    output_data = Dense(input_size, activation='sigmoid')(hidden_2)

    autoencoder = Model(input_data, output_data)
    autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
    autoencoder.fit(x_train, y_train, epochs=30, verbose=0,
                    batch_size=10, validation_data=(x_test, y_test))

    reconstructions = autoencoder.predict(x_test)
    return reconstructions

这是我主要调用算法的代码：

import SAE as FS  # SAE the file of stacked-autoencoder algorithm

print('CurrentFeatureSelection = ', 'Stacked_Autoencoder')
X_train_fs, X_test_fs = FS.StackedAutoencoder(X_train, X_test, y_train, y_test)