![[논문읽기] 07-1. DCGAN MNIST With Tensorflow](https://img1.daumcdn.net/thumb/R750x0/?scode=mtistory2&fname=https%3A%2F%2Ft1.daumcdn.net%2Fcfile%2Ftistory%2F999EE0485D0C72790A)
728x90
반응형
from __future__ import absolute_import, division, print_function, unicode_literals
In [0]:
!pip install tensorflow-gpu==2.0.0-beta0
In [0]:
import tensorflow as tf
tf.__version__
Out[0]:
In [0]:
!pip install imageio
In [0]:
import glob
import imageio
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
from tensorflow.keras import layers
import time
from IPython import display
In [0]:
# Load
(train_images, train_labels),(_,_) = tf.keras.datasets.mnist.load_data()
In [0]:
train_images.shape
Out[0]:
In [0]:
train_images = train_images.reshape(train_images.shape[0],28,28,1).astype('float32')
train_images = (train_images - 127.5) / 127.5 # Normalize the images to [-1,1]
In [0]:
train_images.shape
Out[0]:
In [0]:
BUFFER_SIZE = 60000
BATCH_SIZE = 256
In [0]:
# Batch and shuffle the data
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE)
In [0]:
In [0]:
def make_generator_model():
model = tf.keras.Sequential()
model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())
model.add(layers.Reshape((7, 7, 256)))
assert model.output_shape == (None, 7, 7, 256) # Note: None is the batch size
model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
assert model.output_shape == (None, 7, 7, 128)
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())
model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
assert model.output_shape == (None, 14, 14, 64)
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())
model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
assert model.output_shape == (None, 28, 28, 1)
return model
In [0]:
generator = make_generator_model()
noise = tf.random.normal([1, 100])
generated_image = generator(noise, training=False)
plt.imshow(generated_image[0, :, :, 0], cmap='gray')
Out[0]:
In [0]:
def make_discriminator_model():
model = tf.keras.Sequential()
model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',
input_shape=[28, 28, 1]))
model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))
model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))
model.add(layers.Flatten())
model.add(layers.Dense(1))
return model
In [0]:
discriminator = make_discriminator_model()
decision = discriminator(generated_image)
print (decision)
In [0]:
# This method returns a helper function to compute cross entropy loss
cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
In [0]:
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
In [0]:
def generator_loss(fake_output):
return cross_entropy(tf.ones_like(fake_output), fake_output)
In [0]:
generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)
In [0]:
checkpoint_dir = './training_checkpoints'
checkpoint_prefix = os.path.join(checkpoint_dir, "ckpt")
checkpoint = tf.train.Checkpoint(generator_optimizer=generator_optimizer,
discriminator_optimizer=discriminator_optimizer,
generator=generator,
discriminator=discriminator)
In [0]:
EPOCHS = 50
noise_dim = 100
num_examples_to_generate = 16
# We will reuse this seed overtime (so it's easier)
# to visualize progress in the animated GIF)
seed = tf.random.normal([num_examples_to_generate, noise_dim])
In [0]:
# Notice the use of `tf.function`
# This annotation causes the function to be "compiled".
@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))
In [0]:
def train(dataset, epochs):
for epoch in range(epochs):
start = time.time()
for image_batch in dataset:
train_step(image_batch)
# Produce images for the GIF as we go
display.clear_output(wait=True)
generate_and_save_images(generator,
epoch + 1,
seed)
# Save the model every 15 epochs
if (epoch + 1) % 15 == 0:
checkpoint.save(file_prefix = checkpoint_prefix)
print ('Time for epoch {} is {} sec'.format(epoch + 1, time.time()-start))
# Generate after the final epoch
display.clear_output(wait=True)
generate_and_save_images(generator,
epochs,
seed)
In [0]:
def generate_and_save_images(model, epoch, test_input):
# Notice `training` is set to False.
# This is so all layers run in inference mode (batchnorm).
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()
In [0]:
%%time
train(train_dataset, EPOCHS)
In [0]:
checkpoint.restore(tf.train.latest_checkpoint(checkpoint_dir))
Out[0]:
In [0]:
# GIF
def display_img(epoch_no):
return PIL.Image.open('image_at_epoch_{:04d}.png'.format(epoch_no))
In [0]:
display_img(EPOCHS)
Out[0]:
In [0]:
anim_file = 'dcgan.gif'
with imageio.get_writer(anim_file,mode='I') as writer:
filenames = glob.glob('image*.png')
filenames = sorted(filenames)
last = -1
for i,filename in enumerate(filenames):
frame = 2*(i**0.5)
if round(frame) > round(last):
last = frame
else:
continue
image = imageio.imread(filename)
writer.append_data(image)
image = imageio.imread(filename)
writer.append_data(image)
import IPython
if IPython.version_info > (6,2,0,''):
displya.Image(filename=anim_file)
In [0]:
try:
from google.colab import files
except ImportError:
pass
else:
files.download(anim_file)
Epoch당 결과물을 Gif로 만들어 생성 과정을 살펴볼 수 있습니다.
728x90
반응형