keras使用AutoEncoder对mnist数据降维

import keras
import matplotlib.pyplot as plt
from keras.datasets import mnist

(x_train, _), (x_test, y_test) = mnist.load_data()

x_train = x_train.astype(‘float32‘) / 255
x_test = x_test.astype(‘float32‘) / 255
x_train = x_train.reshape(x_train.shape[0], -1)
x_test = x_test.reshape(x_test.shape[0], -1)
encoding_dim = 2

encoder = keras.models.Sequential([
    keras.layers.Dense(128, activation=‘relu‘),
    keras.layers.Dense(32, activation=‘relu‘),
    keras.layers.Dense(8, activation=‘relu‘),
    keras.layers.Dense(encoding_dim)
])

decoder = keras.models.Sequential([
    keras.layers.Dense(8, activation=‘relu‘),
    keras.layers.Dense(32, activation=‘relu‘),
    keras.layers.Dense(128, activation=‘relu‘),
    keras.layers.Dense(784, activation=‘tanh‘)
])

AutoEncoder = keras.models.Sequential([
    encoder,
    decoder
])
AutoEncoder.compile(optimizer=‘adam‘, loss=‘mse‘)
AutoEncoder.fit(x_train, x_train, epochs=10, batch_size=256)

predict = encoder.predict(x_test)
plt.scatter(predict[:, 0], predict[:, 1], c=y_test)
plt.show()