VAE简单代码python

VAE是一种生成式模型，可以用于生成具有类似于训练数据的新样本。以下是一个简单的VAE代码示例：

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

# 定义编码器模型
latent_dim = 2

encoder_inputs = keras.Input(shape=(28, 28, 1))
x = layers.Conv2D(32, 3, activation="relu", strides=2, padding="same")(encoder_inputs)
x = layers.Conv2D(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Flatten()(x)
x = layers.Dense(16, activation="relu")(x)
z_mean = layers.Dense(latent_dim, name="z_mean")(x)
z_log_var = layers.Dense(latent_dim, name="z_log_var")(x)
encoder = keras.Model(encoder_inputs, [z_mean, z_log_var], name="encoder")

# 定义采样层
class Sampling(layers.Layer):
    """采样层"""

    def call(self, inputs):
        z_mean, z_log_var = inputs
        batch = tf.shape(z_mean)
        dim = tf.shape(z_mean)[1]
        epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
        return z_mean + tf.exp(0.5 * z_log_var) * epsilon

# 定义解码器模型
latent_inputs = keras.Input(shape=(latent_dim,))
x = layers.Dense(7 * 7 * 64, activation="relu")(latent_inputs)
x = layers.Reshape((7, 7, 64))(x)
x = layers.Conv2DTranspose(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Conv2DTranspose(32, 3, activation="relu", strides=2, padding="same")(x)
decoder_outputs = layers.Conv2DTranspose(1, 3, activation="sigmoid", padding="same")(x)
decoder = keras.Model(latent_inputs, decoder_outputs, name="decoder")

# 定义VAE模型
class VAE(keras.Model):
    """VAE模型"""

    def __init__(self, encoder, decoder, **kwargs):
        super(VAE, self).__init__(**kwargs)
        self.encoder = encoder
        self.decoder = decoder
        self.total_loss_tracker = keras.metrics.Mean(name="total_loss")
        self.reconstruction_loss_tracker = keras.metrics.Mean(name="reconstruction_loss")
        self.kl_loss_tracker = keras.metrics.Mean(name="kl_loss")

    @property
    def metrics(self):
        return [
            self.total_loss_tracker,
            self.reconstruction_loss_tracker,
            self.kl_loss_tracker,
        ]

    def train_step(self, data):
        with tf.GradientTape() as tape:
            z_mean, z_log_var = self.encoder(data)
            z = self.sampling([z_mean, z_log_var])
            reconstruction = self.decoder(z)
            reconstruction_loss = tf.reduce_mean(
                keras.losses.binary_crossentropy(data, reconstruction)
            )
            kl_loss = -0.5 * (1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var))
            kl_loss = tf.reduce_mean(tf.reduce_sum(kl_loss, axis=1))
            total_loss = reconstruction_loss + kl_loss
        grads = tape.gradient(total_loss, self.trainable_weights)
        self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
        self.total_loss_tracker.update_state(total_loss)
        self.reconstruction_loss_tracker.update_state(reconstruction_loss)
        self.kl_loss_tracker.update_state(kl_loss)
        return {
            "loss": self.total_loss_tracker.result(),
            "reconstruction_loss": self.reconstruction_loss_tracker.result(),
            "kl_loss": self.kl_loss_tracker.result(),
        }

    def call(self, data):
        z_mean, z_log_var = self.encoder(data)
        z = self.sampling([z_mean, z_log_var])
        return self.decoder(z)

    def sampling(self, args):
        z_mean, z_log_var = args
        batch = tf.shape(z_mean)
        dim = tf.shape(z_mean)
        epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
        return z_mean + tf.exp(0.5 * z_log_var) * epsilon

# 加载MNIST数据集
(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()
all_digits = np.concatenate([x_train, x_test], axis=0)
all_digits.shape

# 数据预处理
all_digits = all_digits.astype("float32") / 255.0
all_digits = np.reshape(all_digits, (-1, 28, 28, 1))

# 训练VAE模型
vae = VAE(encoder=encoder, decoder=decoder)
vae.compile(optimizer=keras.optimizers.Adam())
vae.fit(all_digits, epochs=30, batch_size=128)

# 使用VAE模型生成新的手写数字样本
n = 30 # 生成30个数字样本
digit_size = 28
figure = np.zeros((digit_size * n, digit_size * n))

# 在潜在空间中均匀分布采样n x n个点
grid_x = np.linspace(-4, 4, n)
grid_y = np.linspace(-4, 4, n)[::-1]

for i, yi in enumerate(grid_y):
    for j, xi in enumerate(grid_x):
        z_sample = np.array([[xi, yi]])
        x_decoded = vae.decoder(z_sample)
        digit = x_decoded.numpy().reshape(digit_size, digit_size)
        figure[
            i * digit_size : (i + 1) * digit_size,
            j * digit_size : (j + 1) * digit_size,
        ] = digit

# 显示生成的手写数字样本
plt.figure(figsize=(10, 10))
start_range = digit_size // 2
end_range = n * digit_size + start_range + 1
pixel_range = np.arange(start_range, end_range, digit_size)
sample_range_x = np.round(grid_x, 1)
sample_range_y = np.round(grid_y, 1)
plt.xticks(pixel_range, sample_range_x)
plt.yticks(pixel_range, sample_range_y)
plt.xlabel("z")
plt.ylabel("z")
plt.imshow(figure, cmap="Greys_r")
plt.show()

此示例演示了如何使用Keras和TensorFlow实现一个简单的VAE模型，它可以学习MNIST数据集中的手写数字，并生成类似于这些数字的新样本。