Generative Adversarial Networks (GAN)
By Prof. Seungchul Lee
http://iailab.kaist.ac.kr/
Industrial AI Lab at KAIST
http://iailab.kaist.ac.kr/
Industrial AI Lab at KAIST
Table of Contents
Source
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
- by 최윤제 (고려대 석사생)
- YouTube: https://www.youtube.com/watch?v=odpjk7_tGY0
- Slides: https://www.slideshare.net/NaverEngineering/1-gangenerative-adversarial-network
CSC321 Lecture 19: GAN
- By Prof. Roger Grosse at Univ. of Toronto
- http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/
CS231n: CNN for Visual Recognition
- Lecture 13: Generative Models
- By Prof. Fei-Fei Li at Stanford University
- http://cs231n.stanford.edu/
1. Discriminative Model v.s. Generative Model¶
- Discriminative model
- Cenerative model
2. Density Function Estimation¶
- Probability
- What if $x$ is actual images in the training data? At this point, $x$ can be represented as a (for example) $64\times 64 \times 3$ dimensional vector.
- the following images are some realizations (samples) of $64\times 64 \times 3$ dimensional space
- Probability density function estimation problem
If $P_{\text{model}}(x)$ can be estimated as close to $P_{\text{data}}(x)$, then data can be generated by sampling from $P_{\text{model}}(x)$.
- Note: Kullback–Leibler Divergence is a kind of distance measure between two distributions
Learn determinstic transformation via a neural network
- Start by sampling the code vector $z$ from a simple, fixed distribution such as a uniform distribution or a standard Gaussian $\mathcal{N}(0,I)$
- Then this code vector is passed as input to a deterministic generator network $G$, which produces an output sample $x=G(z)$
- This is how a neural network plays in a generative model (as a nonlinear mapping to a target probability density function)
- An example of a generator network which encodes a univariate distribution with two different modes
- Generative model of high dimensional space
- Generative model of images
- learn a function which maps independent, normally-distributed $z$ values to whatever latent variables might be needed to the model, and then map those latent variables to $x$ (as images)
- first few layers to map the normally distributed $z$ to the latent values
- then, use later layers to map those latent values to an image
3. Generative Adversarial Networks (GAN)¶
In generative modeling, we'd like to train a network that models a distribution, such as a distribution over images.
GANs do not work with any explicit density function !
Instead, take game-theoretic approach
3.1. Adversarial Nets Framework¶
One way to judge the quality of the model is to sample from it.
Model to produce samples which are indistinguishable from the real data, as judged by a discriminator network whose job is to tell real from fake
- The idea behind Generative Adversarial Networks (GANs): train two different networks
- Discriminator network: try to distinguish between real and fake data
- Generator network: try to produce realistic-looking samples to fool the discriminator network
3.2. Objective Function of GAN¶
- Think about a logistic regression classifier (or cross entropy loss $(h(x),y)$)
$$\text{loss} = -y \log h(x) - (1-y) \log (1-h(x))$$
- To train the discriminator
- To train the generator
Non-Saturating Game when the generator is trained
Early in learning, when $G$ is poor, $D$ can reject samples with high confidence because they are clearly different from the training data. In this case, $\log(1-D(G(z)))$ saturates.
- Rather than training $G$ to minimize $\log(1-D(G(z)))$ we can train $G$ to maximize $\log D(G(z))$. This objective function provides much stronger gradients early in learning.
3.3. Soving a MinMax Problem¶
Step 1: Fix $G$ and perform a gradient step to
$$\max_{D} E_{x \sim p_{\text{data}}(x)}\left[\log D(x)\right] + E_{z \sim p_{z}(z)}\left[\log (1-D(G(z)))\right]$$
Step 2: Fix $D$ and perform a gradient step to
$$\max_{G} E_{z \sim p_{z}(z)}\left[\log D(G(z))\right]$$
OR
Step 1: Fix $G$ and perform a gradient step to
$$\min_{D} E_{x \sim p_{\text{data}}(x)}\left[-\log D(x)\right] + E_{z \sim p_{z}(z)}\left[-\log (1-D(G(z)))\right]$$
Step 2: Fix $D$ and perform a gradient step to
$$\min_{G} E_{z \sim p_{z}(z)}\left[-\log D(G(z))\right]$$
In [ ]:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
In [ ]:
(train_x, train_y), _ = tf.keras.datasets.mnist.load_data()
train_x = train_x[np.where(train_y == 2)]
train_x = train_x/255.0
train_x = train_x.reshape(-1, 784)
print('train_iamges :', train_x.shape)
In [ ]:
generator = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 256, activation = 'relu', input_dim = 100),
tf.keras.layers.Dense(units = 784, activation = 'sigmoid')
])
In [ ]:
discriminator = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 256, activation = 'relu', input_dim = 784),
tf.keras.layers.Dense(units = 1, activation = 'sigmoid'),
])
In [ ]:
discriminator.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),
loss = 'binary_crossentropy')
In [ ]:
discriminator.trainable = False
combined_input = tf.keras.layers.Input(shape = (100,))
generated = generator(combined_input)
combined_output = discriminator(generated)
combined = tf.keras.models.Model(inputs = combined_input, outputs = combined_output)
In [ ]:
combined.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0002),
loss = 'binary_crossentropy')
In [ ]:
def make_noise(samples):
return np.random.normal(0, 1, [samples, 100])
In [ ]:
def plot_generated_images(generator, samples = 3):
noise = make_noise(samples)
generated_images = generator.predict(noise)
generated_images = generated_images.reshape(samples, 28, 28)
for i in range(samples):
plt.subplot(1, samples, i+1)
plt.imshow(generated_images[i], 'gray', interpolation = 'nearest')
plt.axis('off')
plt.tight_layout()
plt.show()
Step 1: Fix $G$ and perform a gradient step to
$$\min_{D} E_{x \sim p_{\text{data}}(x)}\left[-\log D(x)\right] + E_{x \sim p_{z}(z)}\left[-\log (1-D(G(z)))\right]$$
Step 2: Fix $D$ and perform a gradient step to
$$\min_{G} E_{x \sim p_{z}(z)}\left[-\log D(G(z))\right]$$
In [ ]:
n_iter = 20000
batch_size = 100
fake = np.zeros(batch_size)
real = np.ones(batch_size)
for i in range(n_iter):
# Train Discriminator
noise = make_noise(batch_size)
generated_images = generator.predict(noise, verbose = 0)
idx = np.random.randint(0, train_x.shape[0], batch_size)
real_images = train_x[idx]
D_loss_real = discriminator.train_on_batch(real_images, real)
D_loss_fake = discriminator.train_on_batch(generated_images, fake)
D_loss = D_loss_real + D_loss_fake
# Train Generator
noise = make_noise(batch_size)
G_loss = combined.train_on_batch(noise, real)
if i % 5000 == 0:
print('Discriminator Loss: ', D_loss)
print('Generator Loss: ', G_loss)
plot_generated_images(generator)
4.2. After Training¶
- After training, use the generator network to generate new data
In [ ]:
plot_generated_images(generator)
5. Conditional GAN¶
In an unconditioned generative model, there is no control on modes of the data being generated.
In the Conditional GAN (CGAN), the generator learns to generate a fake sample with a specific condition or characteristics (such as a label associated with an image or more detailed tag) rather than a generic sample from unknown noise distribution.
Simple modification to the original GAN framework that conditions the model on additional information for better multi-modal learning
Many practical applications of GANs when we have explicit supervision available
In [ ]:
import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
In [ ]:
(train_x, train_y), (test_x, test_y) = tf.keras.datasets.mnist.load_data()
train_x, test_x = train_x/255.0 , test_x/255.0
train_x, test_x = train_x.reshape(-1,784), test_x.reshape(-1,784)
train_y = tf.keras.utils.to_categorical(train_y, num_classes = 10)
test_y = tf.keras.utils.to_categorical(test_y, num_classes = 10)
print('train_x: ', train_x.shape)
print('test_x: ', test_x.shape)
print('train_y: ', train_y.shape)
print('test_y: ', test_y.shape)
In [ ]:
generator_model = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 256, activation = 'relu', input_dim = 138),
tf.keras.layers.Dense(units = 784, activation = 'sigmoid')
])
noise = tf.keras.layers.Input(shape = (128,))
label = tf.keras.layers.Input(shape = (10,))
model_input = tf.keras.layers.concatenate([noise, label], axis = 1)
generated_image = generator_model(model_input)
generator = tf.keras.models.Model(inputs = [noise, label], outputs = generated_image)
In [ ]:
generator.summary()
In [ ]:
discriminator_model = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 256, activation = 'relu', input_dim = 794),
tf.keras.layers.Dense(units = 1, activation = 'sigmoid')
])
input_image = tf.keras.layers.Input(shape = (784,))
label = tf.keras.layers.Input(shape = (10,))
model_input = tf.keras.layers.concatenate([input_image, label], axis = 1)
validity = discriminator_model(model_input)
discriminator = tf.keras.models.Model(inputs = [input_image, label], outputs = validity)
In [ ]:
discriminator.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0002),
loss = ['binary_crossentropy'])
In [ ]:
discriminator.summary()
In [ ]:
discriminator.trainable = False
noise = tf.keras.layers.Input(shape = (128,))
label = tf.keras.layers.Input(shape = (10,))
generated_image = generator([noise, label])
validity = discriminator([generated_image, label])
combined = tf.keras.models.Model(inputs = [noise, label], outputs = validity)
In [ ]:
combined.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0002),
loss = ['binary_crossentropy'])
In [ ]:
combined.summary()
In [ ]:
def create_noise(samples):
return np.random.normal(0, 1, [samples, 128])
In [ ]:
def plot_generated_images(generator):
noise = create_noise(10)
label = np.arange(0, 10).reshape(-1, 1)
label_onehot = np.eye(10)[label.reshape(-1)]
generated_images = generator.predict([noise, label_onehot])
plt.figure(figsize = (12, 3))
for i in range(generated_images.shape[0]):
plt.subplot(1, 10, i + 1)
plt.imshow(generated_images[i].reshape((28, 28)), 'gray', interpolation = 'nearest')
plt.title('Digit: {}'.format(i))
plt.axis('off')
plt.show()
In [ ]:
n_iter = 30000
batch_size = 50
valid = np.ones(batch_size)
fake = np.zeros(batch_size)
for i in range(n_iter):
# Train Discriminator
idx = np.random.randint(0, train_x.shape[0], batch_size)
real_images, labels = train_x[idx], train_y[idx]
noise = create_noise(batch_size)
generated_images = generator.predict([noise,labels], verbose = 0)
d_loss_real = discriminator.train_on_batch([real_images, labels], valid)
d_loss_fake = discriminator.train_on_batch([generated_images, labels], fake)
d_loss = d_loss_real + d_loss_fake
# Train Generator
noise = create_noise(batch_size)
labels = np.random.randint(0, 10, batch_size)
labels_onehot = np.eye(10)[labels]
g_loss = combined.train_on_batch([noise, labels_onehot], valid)
if i % 5000 == 0:
print('Discriminator Loss: ', d_loss)
print('Generator Loss: ', g_loss)
plot_generated_images(generator)
6. InfoGAN (Information Maximizing GAN)¶
In a standard generative model, there is no control on the features of the data being generated.
In the Information Maximizing GAN (InfoGAN), the generator learns to generate a fake sample with latent codes (such as values in the range of -1 to 1) that has interpretable information of the data rather than a generic sample from unknown noise distribution.
The latent code in InfoGAN learns interpretable information from the data using unsupervised learning.
For instance, MNIST digits generated by latent code variation
Simple modification to the original GAN framework, the latent code c is input to the generator and the added Q Net predicts the latent code c of a fake sample x_fake.
The generative model learns interpretable information from the data by itself.
Generator at Conditional GAN
- Feed a random point in latent space and desired number.
- Even if the same latent point is used for two different numbers, the process will work correctly since the latent space only encodes features such as stroke width or angle
Generator at InfoGAN
- Feed a random point in latent space and latent code.
- Even if the same latent point is used, the process will work correctly by controlling the interpretable information in the data through latent code.
6.1. DCGAN (Deep Convolutional GAN)¶
We employed the fully connected neural networks for all the previous GAN examples. DCGAN is a direct extension of GAN, differing primarily in its utilization of convolutional and convolutional-transpose layers in the discriminator and generator.
6.2. InfoGAN Implementation¶
In [ ]:
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
In [ ]:
(train_x, train_y), _ = tf.keras.datasets.mnist.load_data()
train_x = train_x[np.where(train_y == 2)]
train_x = train_x/255.0
train_x = train_x.reshape(-1, 28, 28, 1)
print('train_iamges :', train_x.shape)
In [ ]:
generator = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 1024,
use_bias = False,
input_shape = (62 + 2,)),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.ReLU(),
tf.keras.layers.Dense(units = 7*7*128,
use_bias = False),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.ReLU(),
tf.keras.layers.Reshape((7, 7, 128)),
tf.keras.layers.Conv2DTranspose(64,
(4, 4),
strides = (2, 2),
padding = 'same',
use_bias = False),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.ReLU(),
tf.keras.layers.Conv2DTranspose(1,
(4, 4),
strides = (2, 2),
padding = 'same',
use_bias = False,
activation = 'sigmoid')
])
In [ ]:
extractor = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(64,
(4, 4),
strides = (2, 2),
padding = 'same',
use_bias = False,
input_shape = [28, 28, 1]),
tf.keras.layers.LeakyReLU(),
tf.keras.layers.Conv2D(128,
(4, 4),
strides = (2, 2),
padding = 'same',
use_bias = False),
tf.keras.layers.LayerNormalization(),
tf.keras.layers.LeakyReLU(),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(units = 1024,
use_bias = False),
tf.keras.layers.LayerNormalization(),
tf.keras.layers.LeakyReLU()
])
In [ ]:
d_network = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 1,
input_shape = (1024,),
use_bias = False,
activation = 'sigmoid')
])
In [ ]:
q_network = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 128,
use_bias = False,
input_shape = (1024,)),
tf.keras.layers.LayerNormalization(),
tf.keras.layers.LeakyReLU(),
tf.keras.layers.Dense(units = 2,
use_bias = False)
])
In [ ]:
combined_input = tf.keras.layers.Input(shape = (28, 28, 1))
combined_feature = extractor(combined_input)
combined_output = d_network(combined_feature)
discriminator = tf.keras.models.Model(inputs = combined_input,
outputs = combined_output)
In [ ]:
discriminator.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 2e-4),
loss = 'binary_crossentropy')
In [ ]:
extractor.trainable = False
d_network.trainable = False
combined_input = tf.keras.layers.Input(shape = (62 + 2,))
generated = generator(combined_input)
combined_feature = extractor(generated)
combined_output = d_network(combined_feature)
combined_d = tf.keras.models.Model(inputs = combined_input,
outputs = combined_output)
In [ ]:
combined_d.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-3),
loss = 'binary_crossentropy')
In [ ]:
extractor.trainable = False
d_network.trainable = False
combined_input = tf.keras.layers.Input(shape = (62 + 2,))
generated = generator(combined_input)
combined_feature = extractor(generated)
combined_latent = q_network(combined_feature)
combined_q = tf.keras.models.Model(inputs = combined_input,
outputs = combined_latent)
In [ ]:
combined_q.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-3),
loss = 'mean_squared_error')
In [ ]:
def make_noise(samples):
return np.random.uniform(-1, 1, size = [samples, 62])
def make_code(samples):
return 2*np.random.rand(samples, 2) - 1
In [ ]:
def plot_generated_images(generator):
z = np.random.randn(1, 62).repeat(5, axis = 0)
c = np.stack([np.linspace(-1, 1, 5), np.zeros(5)]).T
noise = np.concatenate([z, c], -1)
generated_images = generator.predict(noise, verbose = 0)
generated_images = generated_images.reshape(5, 28, 28)
print('')
print('Continuous Latent Code 1')
for i in range(5):
plt.subplot(1, 5, i+1)
plt.imshow(generated_images[i], 'gray', interpolation = 'nearest')
plt.axis('off')
plt.tight_layout()
plt.show()
z = np.random.randn(1, 62).repeat(5, axis = 0)
c = np.stack([np.zeros(5), np.linspace(-1, 1, 5)]).T
noise = np.concatenate([z, c], -1)
generated_images = generator.predict(noise, verbose = 0)
generated_images = generated_images.reshape(5, 28, 28)
print('Continuous Latent Code 2')
for i in range(5):
plt.subplot(1, 5, i+1)
plt.imshow(generated_images[i], 'gray', interpolation = 'nearest')
plt.axis('off')
plt.tight_layout()
plt.show()
print('')
In [ ]:
n_iter = 5000
batch_size = 256
real = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for i in range(n_iter):
# Train Discriminator
for _ in range(2):
z = make_noise(batch_size)
c = make_code(batch_size)
noise = np.concatenate([z, c], -1)
generated_images = generator.predict(noise, verbose = 0)
idx = np.random.choice(len(train_x), batch_size, replace = False)
real_images = train_x[idx]
D_loss_real = discriminator.train_on_batch(real_images, real)
D_loss_fake = discriminator.train_on_batch(generated_images, fake)
D_loss = D_loss_real + D_loss_fake
# Train Generator & Q Net
for _ in range(1):
z = make_noise(batch_size)
c = make_code(batch_size)
noise = np.concatenate([z, c], -1)
G_loss = combined_d.train_on_batch(noise, real)
Q_loss = combined_q.train_on_batch(noise, c)
# Print Loss
if (i + 1) % 500 == 0:
print('Epoch: {:5d} | Discriminator Loss: {:.3f} | Generator Loss: {:.3f} | Q Net Loss: {:.3f}'.format(i + 1, D_loss, G_loss, Q_loss))
plot_generated_images(generator)
In [ ]:
images_save_1 = []
images_save_2 = []
for i in range(8):
z = np.random.randn(1, 62).repeat(8, axis = 0)
# Continuous Latent Code 1
c = np.stack([np.linspace(-1, 1, 8), np.zeros(8)]).T
noise = np.concatenate([z, c], -1)
generated_images = generator.predict(noise, verbose=0)
generated_images = generated_images.reshape(8, 28, 28)
images_save_1.append(generated_images)
# Continuous Latent Code 2
c = np.stack([np.zeros(8), np.linspace(-1, 1, 8)]).T
noise = np.concatenate([z, c], -1)
generated_images = generator.predict(noise, verbose=0)
generated_images = generated_images.reshape(8, 28, 28)
images_save_2.append(generated_images)
In [ ]:
print('Continuous Latent Code 1')
fig, ax = plt.subplots(8, 8, figsize = (10, 10))
for i in range(8):
for j in range(8):
ax[i][j].imshow(images_save_1[i][j], 'gray')
ax[i][j].set_xticks([])
ax[i][j].set_yticks([])
plt.show()
In [ ]:
print('Continuous Latent Code 2')
fig, ax = plt.subplots(8, 8, figsize = (10, 10))
for i in range(8):
for j in range(8):
ax[i][j].imshow(images_save_2[i][j], 'gray')
ax[i][j].set_xticks([])
ax[i][j].set_yticks([])
plt.show()
7. CycleGAN¶
Change the style of image to another style
- Monet to photos
- Zebras to horses
- Summer to winter
Limitation of paired datasets
- Impossible to collect paired datasets in most of the cases.
Start from naive GAN
- Given an image X (Horse), transform it into the target image Y (Zebra)
Utilize two generators and cycle-consistency loss to preserve the contents of input images.
$G_{XY}(X \rightarrow Y)$ and $G_{YX}(Y \rightarrow X)$
Cycle-consistency loss: $G_{YX}(G_{XY}(X))=X$
8. Adversarial Autoencoder (AAE)¶
8.1. Limitation of Autoencoder¶
Autoencoder: Manifold learning model (≠ Generative model)
- Manifold is randomly generated for each training
- Hard to generate new data from the manifold
Generate Data from Controlled Latent Space
- Encode data into a controllable latent space
- Generate new data from the controlled space
8.2. Adversarial Autoencoder¶
8.3. Incorporating Label Information¶
Disentangled Latent Representation
8.4. Implementation of AAE¶
In [ ]:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import random
In [ ]:
mnist = tf.keras.datasets.mnist
(train_x, train_y), (test_x, test_y) = mnist.load_data()
(train_x, train_y), (test_x, test_y) = mnist.load_data()
train_x, test_x = train_x.reshape(-1, 784)/255.0, test_x.reshape(-1, 784)/255.0
In [ ]:
# Use only 0,1,2,3,4,5 digits to visualize latent sapce
train_idx0 = np.array(np.where(train_y == 0))
train_idx1 = np.array(np.where(train_y == 1))
train_idx2 = np.array(np.where(train_y == 2))
train_idx3 = np.array(np.where(train_y == 3))
train_idx4 = np.array(np.where(train_y == 4))
train_idx5 = np.array(np.where(train_y == 5))
train_idx = np.sort(np.concatenate((train_idx0, train_idx1, train_idx2, train_idx3, train_idx4, train_idx5), axis = None))
test_idx0 = np.array(np.where(test_y == 0))
test_idx1 = np.array(np.where(test_y == 1))
test_idx2 = np.array(np.where(test_y == 2))
test_idx3 = np.array(np.where(test_y == 3))
test_idx4 = np.array(np.where(test_y == 4))
test_idx5 = np.array(np.where(test_y == 5))
test_idx = np.sort(np.concatenate((test_idx0, test_idx1, test_idx2, test_idx3, test_idx4, test_idx5), axis = None))
train_imgs = train_x[train_idx]
train_labels = train_y[train_idx]
test_imgs = test_x[test_idx]
test_labels = test_y[test_idx]
n_train = train_imgs.shape[0]
n_test = test_imgs.shape[0]
print ("The number of training images : {}, shape : {}".format(n_train, train_imgs.shape))
print ("The number of testing images : {}, shape : {}".format(n_test, test_imgs.shape))
In [ ]:
# Define Structure
# Encoder
encoder = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 500, activation = 'relu', input_shape = (784,)),
tf.keras.layers.Dense(units = 300, activation = 'relu'),
tf.keras.layers.Dense(units = 2, activation = None)
])
# Decoder
decoder = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 300, activation = 'relu', input_shape = (2,)),
tf.keras.layers.Dense(units = 500, activation = 'relu'),
tf.keras.layers.Dense(units = 784, activation = None)
])
# Discriminator
discriminator = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 100, activation = 'relu', input_shape = (2,)),
tf.keras.layers.Dense(units = 100, activation = 'relu'),
tf.keras.layers.Dense(units = 1, activation = 'sigmoid')
])
In [ ]:
autoencoder = tf.keras.models.Sequential([encoder, decoder])
autoencoder.compile(optimizer = tf.keras.optimizers.Adam(0.0005),
loss = 'mean_squared_error')
encoder.trainable = False
discriminator.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0005),
loss = 'binary_crossentropy')
discriminator.trainable = False
encoder.trainable = True
combined_input = tf.keras.layers.Input(shape = (28*28,))
latent_variable = encoder(combined_input)
combined_output = discriminator(latent_variable )
combined = tf.keras.models.Model(inputs = combined_input, outputs = combined_output)
combined.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0005),
loss = 'binary_crossentropy')
In [ ]:
def gaussian_mixture_sampler(batchsize, ndim, num_labels):
if ndim % 2 != 0:
raise Exception("ndim must be a multiple of 2.")
def sample(x, y, label, num_labels):
shift = 1.4
r = 2 * np.pi / float(num_labels) * float(label)
new_x = x * np.cos(r) - y * np.sin(r)
new_y = x * np.sin(r) + y * np.cos(r)
new_x += shift * np.cos(r)
new_y += shift * np.sin(r)
return np.array([new_x, new_y]).reshape((2,)), tf.one_hot(label, num_labels + 1)
x_var = 0.3
y_var = 0.05
x = np.random.normal(0, x_var, (batchsize, ndim // 2))
y = np.random.normal(0, y_var, (batchsize, ndim // 2))
z = np.empty((batchsize, ndim), dtype = np.float32)
z_label = np.empty((batchsize, num_labels + 1), dtype = np.float32)
for batch in range(batchsize):
for zi in range(ndim // 2):
z[batch, zi*2:zi*2+2], z_label[batch] = sample(x[batch, zi], y[batch, zi], random.randint(0, num_labels - 1), num_labels)
return z, z_label
In [ ]:
prior, one_hot_label = gaussian_mixture_sampler(1000, 2, 6)
c = np.array(['r', 'g', 'b', 'c', 'y', 'k'])
plt.scatter(prior[:, 0], prior[:, 1], s = 1, c = c[list(np.argmax(one_hot_label, 1))])
plt.show()
In [ ]:
def plot_latent_space(encoder, samples = 1000):
idx = np.random.randint(0, train_imgs.shape[0], samples)
latent_fake = encoder.predict(train_imgs[idx], verbose = 0)
c = np.array(['r', 'g', 'b', 'c', 'y', 'k'])
for i, el in enumerate([0, 1, 2, 3, 4, 5]):
label_idx = np.where(train_labels[idx] == el)[0]
plt.scatter(latent_fake[label_idx, 0], latent_fake[label_idx, 1], s = 1, label = el, c = c[i])
plt.legend()
plt.xticks([])
plt.yticks([])
plt.show()
In [ ]:
n_iter = 10000
batch_size = 100
fake = np.zeros(batch_size)
real = np.ones(batch_size)
for i in range(n_iter):
idx = np.random.randint(0, train_imgs.shape[0], batch_size)
# Train Autoencoder
AE_loss = autoencoder.train_on_batch(train_imgs[idx], train_imgs[idx])
# Train Discriminator
latent_true, _ = gaussian_mixture_sampler(batch_size, 2, 6)
latent_fake = encoder.predict(train_imgs[idx], verbose = 0)
D_loss_real = discriminator.train_on_batch(latent_true, real)
D_loss_fake = discriminator.train_on_batch(latent_fake, fake)
D_loss = D_loss_real + D_loss_fake
# Train Generator
idx = np.random.randint(0, train_imgs.shape[0], batch_size)
Adv_loss = combined.train_on_batch(train_imgs[idx], real)
if i % 1000 == 0:
print('Autoencoder Loss: ', AE_loss)
print('Discriminator Loss: ', D_loss)
print('Adversarial Loss: ', Adv_loss)
plot_latent_space(encoder)
In [ ]:
# Encoder
encoder = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 500, activation = 'relu', input_shape = (784,)),
tf.keras.layers.Dense(units = 300, activation = 'relu'),
tf.keras.layers.Dense(units = 2, activation = None)
])
# Decoder
decoder = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 300, activation = 'relu', input_shape = (2,)),
tf.keras.layers.Dense(units = 500, activation = 'relu'),
tf.keras.layers.Dense(units = 784, activation = None)
])
# discriminator_label
discriminator_label = tf.keras.models.Sequential([
tf.keras.layers.Dense(units = 100, activation = 'relu', input_shape = (2 + 6 + 1,)),
tf.keras.layers.Dense(units = 100, activation = 'relu'),
tf.keras.layers.Dense(units = 1, activation = 'sigmoid')
])
In [ ]:
autoencoder = tf.keras.models.Sequential([encoder, decoder])
autoencoder.compile(optimizer = tf.keras.optimizers.Adam(0.0005),
loss = 'mean_squared_error')
encoder.trainable = False
discriminator_label.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0005),
loss = 'binary_crossentropy')
discriminator_label.trainable = False
encoder.trainable = True
combined_input = tf.keras.layers.Input(shape = (28*28 + 6 + 1,))
latent_variable = encoder(combined_input[:, :28*28])
latent_label = tf.concat([latent_variable, combined_input[:, 28*28:]], 1)
combined_label_output = discriminator_label(latent_label)
combined_label = tf.keras.models.Model(inputs = combined_input, outputs = combined_label_output)
combined_label.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0005),
loss = 'binary_crossentropy')
In [ ]:
n_iter = 10000
batch_size = 100
fake = np.zeros(batch_size)
real = np.ones(batch_size)
for i in range(n_iter):
idx = np.random.randint(0, train_imgs.shape[0], batch_size)
# Train Autoencoder
AE_loss = autoencoder.train_on_batch(train_imgs[idx], train_imgs[idx])
# Train Discriminator
# positive phase
latent_true, one_hot_true_label = gaussian_mixture_sampler(batch_size, 2, 6)
latent_true = tf.concat([latent_true, one_hot_true_label], 1)
D_loss_real = discriminator_label.train_on_batch(latent_true, real)
latent_true, one_hot_true_label = gaussian_mixture_sampler(batch_size, 2, 6)
one_hot_fake_label = tf.one_hot([6] * batch_size, 6 + 1)
latent_true = tf.concat([latent_true, one_hot_fake_label], 1)
D_loss_real += discriminator_label.train_on_batch(latent_true, real)
latent_fake = encoder.predict(train_imgs[idx], verbose = 0)
one_hot_fake_label = tf.one_hot([6] * batch_size, 6 + 1)
latent_fake = tf.concat([latent_fake, one_hot_fake_label], 1)
D_loss_fake = discriminator_label.train_on_batch(latent_fake, fake)
D_loss = D_loss_real + D_loss_fake
# Train Generator
idx = np.random.randint(0, train_imgs.shape[0], batch_size)
one_hot_fake_label = tf.one_hot([6] * batch_size, 6 + 1)
train_input = tf.concat([train_imgs[idx], one_hot_fake_label], 1)
Adv_loss = combined_label.train_on_batch(train_input, real)
if i % 1000 == 0:
print('Autoencoder Loss: ', AE_loss)
print('Discriminator Loss: ', D_loss)
print('Adversarial Loss: ', Adv_loss)
plot_latent_space(encoder)
In [1]:
%%javascript
$.getScript('https://kmahelona.github.io/ipython_notebook_goodies/ipython_notebook_toc.js')