自编码器AutoEncoder

最新推荐文章于 2024-09-23 22:44:18 发布

GSAU-深蓝工作室

最新推荐文章于 2024-09-23 22:44:18 发布

阅读量413

点赞数

文章标签： tensorflow 人工智能 python auto-encoder

本文链接：https://blog.csdn.net/weixin_40604528/article/details/121181216

版权

该博客介绍了如何利用TensorFlow构建自编码器（AE）和变分自编码器（VAE）模型。首先，通过自编码器进行图像重构，模型包括编码器和解码器，训练过程中采用二元交叉熵损失函数。然后，变分自编码器增加了重参数化技巧，用以处理隐变量的不确定性，同时计算了KL散度以保持生成分布与标准正态分布之间的距离。博客中还展示了训练过程中的损失变化，并保存了样本图像。

摘要由CSDN通过智能技术生成

代码实现部分：

autoencoder.py

import  os
import  tensorflow as tf
import  numpy as np
from    tensorflow import keras
from    tensorflow.keras import Sequential, layers
from    PIL import Image
from    matplotlib import pyplot as plt



tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')


def save_images(imgs, name):
    new_im = Image.new('L', (280, 280))

    index = 0
    for i in range(0, 280, 28):
        for j in range(0, 280, 28):
            im = imgs[index]
            im = Image.fromarray(im, mode='L')
            new_im.paste(im, (i, j))
            index += 1

    new_im.save(name)


h_dim = 20
batchsz = 512
lr = 1e-3


(x_train, y_train), (x_test, y_test) = keras.datasets.fashion_mnist.load_data()
x_train, x_test = x_train.astype(np.float32) / 255., x_test.astype(np.float32) / 255.
# we do not need label
train_db = tf.data.Dataset.from_tensor_slices(x_train)
train_db = train_db.shuffle(batchsz * 5).batch(batchsz)
test_db = tf.data.Dataset.from_tensor_slices(x_test)
test_db = test_db.batch(batchsz)

print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)



class AE(keras.Model):

    def __init__(self):
        super(AE, self).__init__()

        # Encoders
        self.encoder = Sequential([
            layers.Dense(256, activation=tf.nn.relu),
            layers.Dense(128, activation=tf.nn.relu),
            layers.Dense(h_dim)
        ])

        # Decoders
        self.decoder = Sequential([
            layers.Dense(128, activation=tf.nn.relu),
            layers.Dense(256, activation=tf.nn.relu),
            layers.Dense(784)
        ])


    def call(self, inputs, training=None):
        # [b, 784] => [b, 10]
        h = self.encoder(inputs)
        # [b, 10] => [b, 784]
        x_hat = self.decoder(h)

        return x_hat



model = AE()
model.build(input_shape=(None, 784))
model.summary()

optimizer = tf.optimizers.Adam(lr=lr)

for epoch in range(100):

    for step, x in enumerate(train_db):

        #[b, 28, 28] => [b, 784]
        x = tf.reshape(x, [-1, 784])

        with tf.GradientTape() as tape:
            x_rec_logits = model(x)

            rec_loss = tf.losses.binary_crossentropy(x, x_rec_logits, from_logits=True)
            rec_loss = tf.reduce_mean(rec_loss)

        grads = tape.gradient(rec_loss, model.trainable_variables)
        optimizer.apply_gradients(zip(grads, model.trainable_variables))


        if step % 100 ==0:
            print(epoch, step, float(rec_loss))


        # evaluation
        x = next(iter(test_db))
        logits = model(tf.reshape(x, [-1, 784]))
        x_hat = tf.sigmoid(logits)
        # [b, 784] => [b, 28, 28]
        x_hat = tf.reshape(x_hat, [-1, 28, 28])

        # [b, 28, 28] => [2b, 28, 28]
        x_concat = tf.concat([x, x_hat], axis=0)
        x_concat = x_hat
        x_concat = x_concat.numpy() * 255.
        x_concat = x_concat.astype(np.uint8)
        save_images(x_concat, 'S:/ae_images/rec_epoch_%d.png'%epoch)

age.py

import  os
import  tensorflow as tf
import  numpy as np
from    tensorflow import keras
from    tensorflow.keras import Sequential, layers
from    PIL import Image
from    matplotlib import pyplot as plt



tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')


def save_images(imgs, name):
    new_im = Image.new('L', (280, 280))

    index = 0
    for i in range(0, 280, 28):
        for j in range(0, 280, 28):
            im = imgs[index]
            im = Image.fromarray(im, mode='L')
            new_im.paste(im, (i, j))
            index += 1

    new_im.save(name)


h_dim = 20
batchsz = 512
lr = 1e-3


(x_train, y_train), (x_test, y_test) = keras.datasets.fashion_mnist.load_data()
x_train, x_test = x_train.astype(np.float32) / 255., x_test.astype(np.float32) / 255.
# we do not need label
train_db = tf.data.Dataset.from_tensor_slices(x_train)
train_db = train_db.shuffle(batchsz * 5).batch(batchsz)
test_db = tf.data.Dataset.from_tensor_slices(x_test)
test_db = test_db.batch(batchsz)

print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

z_dim = 10

class VAE(keras.Model):

    def __init__(self):
        super(VAE, self).__init__()

        # Encoder
        self.fc1 = layers.Dense(128)
        self.fc2 = layers.Dense(z_dim) # get mean prediction
        self.fc3 = layers.Dense(z_dim)

        # Decoder
        self.fc4 = layers.Dense(128)
        self.fc5 = layers.Dense(784)

    def encoder(self, x):

        h = tf.nn.relu(self.fc1(x))
        # get mean
        mu = self.fc2(h)
        # get variance
        log_var = self.fc3(h)

        return mu, log_var

    def decoder(self, z):

        out = tf.nn.relu(self.fc4(z))
        out = self.fc5(out)

        return out

    def reparameterize(self, mu, log_var):

        eps = tf.random.normal(log_var.shape)

        std = tf.exp(log_var*0.5)

        z = mu + std * eps
        return z

    def call(self, inputs, training=None):

        # [b, 784] => [b, z_dim], [b, z_dim]
        mu, log_var = self.encoder(inputs)
        # reparameterization trick
        z = self.reparameterize(mu, log_var)

        x_hat = self.decoder(z)

        return x_hat, mu, log_var


model = VAE()
model.build(input_shape=(4, 784))
optimizer = tf.optimizers.Adam(lr)

for epoch in range(1000):

    for step, x in enumerate(train_db):

        x = tf.reshape(x, [-1, 784])

        with tf.GradientTape() as tape:
            x_rec_logits, mu, log_var = model(x)

            rec_loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=x, logits=x_rec_logits)
            rec_loss = tf.reduce_sum(rec_loss) / x.shape[0]

            # compute kl divergence (mu, var) ~ N (0, 1)
            # https://stats.stackexchange.com/questions/7440/kl-divergence-between-two-univariate-gaussians
            kl_div = -0.5 * (log_var + 1 - mu**2 - tf.exp(log_var))
            kl_div = tf.reduce_sum(kl_div) / x.shape[0]

            loss = rec_loss + 1. * kl_div

        grads = tape.gradient(loss, model.trainable_variables)
        optimizer.apply_gradients(zip(grads, model.trainable_variables))


        if step % 100 == 0:
            print(epoch, step, 'kl div:', float(kl_div), 'rec loss:', float(rec_loss))


    # evaluation
    z = tf.random.normal((batchsz, z_dim))
    logits = model.decoder(z)
    x_hat = tf.sigmoid(logits)
    x_hat = tf.reshape(x_hat, [-1, 28, 28]).numpy() *255.
    x_hat = x_hat.astype(np.uint8)
    save_images(x_hat, 'S:/vae_images/sampled_epoch%d.png'%epoch)

    x = next(iter(test_db))
    x = tf.reshape(x, [-1, 784])
    x_hat_logits, _, _ = model(x)
    x_hat = tf.sigmoid(x_hat_logits)
    x_hat = tf.reshape(x_hat, [-1, 28, 28]).numpy() *255.
    x_hat = x_hat.astype(np.uint8)
    save_images(x_hat, 'S:/vae_images/rec_epoch%d.png'%epoch)

分享视频：

自编码器AutoEncoder

分享人：尚皓玺

分享时间：2021/11/03

分享平台：腾讯会议