在Keras中创建VAE时出现调用方法未实现运行时错误。模型子类化

import tensorflow as tf
from tensorflow.keras import layers

class VAE(tf.keras.Model):
    def __init__(self, latent_dim):
        super(VAE, self).__init__()
        self.latent_dim = latent_dim
        self.encoder = tf.keras.Sequential([
            layers.InputLayer(input_shape=(28, 28, 1)),
            layers.Flatten(),
            layers.Dense(256, activation='relu'),
            layers.Dense(128, activation='relu'),
            layers.Dense(2 * latent_dim)  # 输出潜在空间的均值和方差
        ])
        self.decoder = tf.keras.Sequential([
            layers.InputLayer(input_shape=(latent_dim,)),
            layers.Dense(128, activation='relu'),
            layers.Dense(256, activation='relu'),
            layers.Dense(28 * 28, activation='sigmoid'),
            layers.Reshape((28, 28, 1))
        ])

    def encode(self, x):
        mean, logvar = tf.split(self.encoder(x), num_or_size_splits=2, axis=1)
        return mean, logvar

    def reparameterize(self, mean, logvar):
        eps = tf.random.normal(shape=mean.shape)
        return eps * tf.exp(logvar * 0.5) + mean

    def decode(self, z):
        return self.decoder(z)

    def call(self, x):
        mean, logvar = self.encode(x)
        z = self.reparameterize(mean, logvar)
        reconstructed = self.decode(z)
        return reconstructed

# 创建VAE模型实例
latent_dim = 10
vae = VAE(latent_dim)

# 编译模型
vae.compile(optimizer=tf.keras.optimizers.Adam(), loss=tf.keras.losses.MeanSquaredError())

# 训练模型
vae.fit(train_dataset, epochs=10, validation_data=val_dataset)