Voici un tutoriel de base sur la mise en place et l’entraînement de modèles de génération d’images à l’aide de réseaux adversoriels génératifs (GANs) avec TensorFlow et PyTorch. Ce guide suppose une compréhension fondamentale de Python et des concepts de base de l’apprentissage automatique.
1. Configuration de votre environnement
Installation des bibliothèques nécessaires
Vous devez vous assurer que Python est installé. Vous devrez également installer TensorFlow ou PyTorch ainsi que d’autres bibliothèques essentielles.
Pour TensorFlow:
Shell
pip install tensorflow numpy matplotlibPour PyTorch:
Shell
pip install torch torchvision numpy matplotlibImporter les bibliothèques
Python
import numpy as np
import matplotlib.pyplot as plt
# Pour TensorFlow
import tensorflow as tf
from tensorflow.keras.layers import Dense, Reshape, Flatten, Conv2D, Conv2DTranspose, LeakyReLU, Dropout
from tensorflow.keras.models import Sequential
# Pour PyTorch
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
2. Charger et préparer le jeu de données
En utilisant le jeu de données MNIST comme exemple.
Pour TensorFlow:
Python
(train_images, train_labels), (_, _) = tf.keras.datasets.mnist.load_data()
train_images = train_images.reshape(train_images.shape[0], 28, 28, 1).astype('float32')
train_images = (train_images - 127.5) / 127.5 # Normalize to [-1, 1]
BUFFER_SIZE = 60000
BATCH_SIZE = 256
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE)
Pour PyTorch:
Python
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
train_loader = DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)
3. Définir l’architecture du GAN
Modèle générateur
Pour TensorFlow:
Python
def make_generator_model():
model = Sequential()
model.add(Dense(7*7*256, use_bias=False, input_shape=(100,)))
model.add(LeakyReLU())
model.add(Reshape((7, 7, 256)))
model.add(Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
model.add(LeakyReLU())
model.add(Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
model.add(LeakyReLU())
model.add(Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
return model
Pour PyTorch:
Python
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
self.main = nn.Sequential(
nn.ConvTranspose2d(100, 256, 7, 1, 0, bias=False),
nn.BatchNorm2d(256),
nn.ReLU(True),
nn.ConvTranspose2d(256, 128, 4, 2, 1, bias=False),
nn.BatchNorm2d(128),
nn.ReLU(True),
nn.ConvTranspose2d(128, 64, 4, 2, 1, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(True),
nn.ConvTranspose2d(64, 1, 4, 2, 1, bias=False),
nn.Tanh()
)
def forward(self, input):
return self.main(input)
Modèle discriminateur
Pour TensorFlow:
Python
def make_discriminator_model():
model = Sequential()
model.add(Conv2D(64, (5, 5), strides=(2, 2), padding='same', input_shape=[28, 28, 1]))
model.add(LeakyReLU())
model.add(Dropout(0.3))
model.add(Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
model.add(LeakyReLU())
model.add(Dropout(0.3))
model.add(Flatten())
model.add(Dense(1))
return model
Pour PyTorch:
Python
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.main = nn.Sequential(
nn.Conv2d(1, 64, 4, 2, 1, bias=False),
nn.LeakyReLU(0.2, inplace=True),
nn.Conv2d(64, 128, 4, 2, 1, bias=False),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2, inplace=True),
nn.Conv2d(128, 256, 4, 2, 1, bias=False),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2, inplace=True),
nn.Conv2d(256, 1, 4, 1, 0, bias=False),
nn.Sigmoid()
)
def forward(self, input):
return self.main(input)
4. Définir la perte et les optimiseurs
Pour TensorFlow:
Python
cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
def discriminator_loss(real_output, fake_output):
real_loss = cross_entropy(tf.ones_like(real_output), real_output)
fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
total_loss = real_loss + fake_loss
return total_loss
def generator_loss(fake_output):
return cross_entropy(tf.ones_like(fake_output), fake_output)
generator = make_generator_model()
discriminator = make_discriminator_model()
generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)
Pour PyTorch:
Python
criterion = nn.BCELoss()
fixed_noise = torch.randn(64, 100, 1, 1, device=device)
real_label = 1.
fake_label = 0.
optimizerD = optim.Adam(discriminator.parameters(), lr=0.0002, betas=(0.5, 0.999))
optimizerG = optim.Adam(generator.parameters(), lr=0.0002, betas=(0.5, 0.999))
5. Entraînement du GAN
Pour TensorFlow:
Python
EPOCHS = 50
noise_dim = 100
num_examples_to_generate = 16
seed = tf.random.normal([num_examples_to_generate, noise_dim])
@tf.function
def train_step(images):
noise = tf.random.normal([BATCH_SIZE, noise_dim])
with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
generated_images = generator(noise, training=True)
real_output = discriminator(images, training=True)
fake_output = discriminator(generated_images, training=True)
gen_loss = generator_loss(fake_output)
disc_loss = discriminator_loss(real_output, fake_output)
gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)
generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))
def train(dataset, epochs):
for epoch in range(epochs):
for image_batch in dataset:
train_step(image_batch)
display.clear_output(wait=True)
generate_and_save_images(generator, epoch + 1, seed)
print ('Epoch {} completed'.format(epoch+1))
def generate_and_save_images(model, epoch, test_input):
predictions = model(test_input, training=False)
fig = plt.figure(figsize=(4, 4))
for i in range(predictions.shape[0]):
plt.subplot(4, 4, i+1)
plt.imshow(predictions[i, :, :, 0] * 127.5 + 127.5, cmap='gray')
plt.axis('off')
plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
plt.show()
train(train_dataset, EPOCHS)
Pour PyTorch :
Python
num_epochs = 5
for epoch in range(num_epochs):
for i, data in enumerate(train_loader, 0):
# Mise à jour du discriminateur : maximiser log(D(x)) + log(1 - D(G(z)))
discriminator.zero_grad()
real_cpu = data[0].to(device)
b_size = real_cpu.size(0)
label = torch.full((b_size,), real_label, dtype=torch.float, device=device)
output = discriminator(real_cpu).view(-1)
errD_real = criterion(output, label)
errD_real.backward()
D_x = output.mean().item()
noise = torch.randn(b_size, 100, 1, 1, device=device)
fake = generator(noise)
label.fill_(fake_label)
output = discriminator(fake.detach()).view(-1)
errD_fake = criterion(output, label)
errD_fake.backward()
D_G_z1 = output.mean().item()
errD = errD_real + errD_fake
optimizerD.step()
# Mise à jour du générateur : maximiser log(D(G(z)))
generator.zero_grad()
label.fill_(real_label)
output = discriminator(fake).view(-1)
errG = criterion(output, label)
errG.backward()
D_G_z2 = output.mean().item()
optimizerG.step()
if i % 100 == 0:
print(f'[{epoch}/{num_epochs}][{i}/{len(train_loader)}] '
f'Loss_D: {errD.item():.4f} Loss_G: {errG.item():.4f} '
f'D(x): {D_x:.4f} D(G(z)): {D_G_z1:.4f} / {D_G_z2:.4f}')
with torch.no_grad():
fake = generator(fixed_noise).detach().cpu()
plt.figure(figsize=(10,10))
plt.axis("off")
plt.title("Fake Images")
plt.imshow(np.transpose(vutils.make_grid(fake, padding=2, normalize=True).cpu(),(1,2,0)))
plt.show()
Ces tutoriels fournissent un point de départ pour configurer et entraîner des modèles GAN de base à la fois dans TensorFlow et PyTorch. L’ajustement des paramètres et l’exploration d’architectures plus complexes peuvent améliorer la compréhension et les résultats.
Source:
https://dzone.com/articles/step-by-step-guide-to-setting-up-and-training