In [1]:
data_dir = './data'
# FloydHub - Use with data ID "R5KrjnANiKVhLWAkpXhNBe"
#data_dir = '/input'
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper
helper.download_extract('mnist', data_dir)
helper.download_extract('celeba', data_dir)
In [2]:
show_n_images = 25
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
import os
from glob import glob
from matplotlib import pyplot
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')
pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')
Out[2]:
In [3]:
show_n_images = 25
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')
pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))
Out[3]:
In [4]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf
# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer. You are using {}'.format(tf.__version__)
print('TensorFlow Version: {}'.format(tf.__version__))
# Check for a GPU
if not tf.test.gpu_device_name():
warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
In [5]:
import problem_unittests as tests
def model_inputs(image_width, image_height, image_channels, z_dim):
"""
Create the model inputs
:param image_width: The input image width
:param image_height: The input image height
:param image_channels: The number of image channels
:param z_dim: The dimension of Z
:return: Tuple of (tensor of real input images, tensor of z data, learning rate)
"""
# TODO: Implement Function
tensor_of_real_input_images = tf.placeholder(tf.float32, (None, image_width, image_height, image_channels), name='input_real')
tensor_of_z_data = tf.placeholder(tf.float32, (None, z_dim), name='input_z')
learning_rate = tf.placeholder(tf.float32, [], 'Learning_Rate')
return (tensor_of_real_input_images, tensor_of_z_data, learning_rate)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)
In [6]:
def discriminator(images, reuse=False):
"""
Create the discriminator network
:param image: Tensor of input image(s)
:param reuse: Boolean if the weights should be reused
:return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)
"""
# TODO: Implement Function
with tf.variable_scope('discriminator', reuse=reuse):
# Input layer is 32x32x3
x1 = tf.layers.conv2d(images, 64, 5, strides=2, padding='same')
relu1 = tf.maximum(0.2 * x1, x1)
# 16x16x32
x2 = tf.layers.conv2d(relu1, 128, 5, strides=2, padding='same')
bn2 = tf.layers.batch_normalization(x2, training=True)
relu2 = tf.maximum(0.2 * bn2, bn2)
# 8x8x128
x3 = tf.layers.conv2d(relu2, 256, 5, strides=2, padding='same')
bn3 = tf.layers.batch_normalization(x3, training=True)
relu3 = tf.maximum(0.2 * bn3, bn3)
# 4x4x256
# Flatten it
flat = tf.reshape(relu3, (-1, 4*4*256))
logits = tf.layers.dense(flat, 1)
out = tf.sigmoid(logits)
return out, logits
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_discriminator(discriminator, tf)
In [7]:
def generator(z, out_channel_dim, is_train=True):
"""
Create the generator network
:param z: Input z
:param out_channel_dim: The number of channels in the output image
:param is_train: Boolean if generator is being used for training
:return: The tensor output of the generator
"""
# TODO: Implement Function
alpha = 0.2
with tf.variable_scope('generator', reuse = not is_train):
x1 = tf.layers.dense(z, 2*2*512)
x1 = tf.reshape(x1, (-1, 2, 2, 512))
x1 = tf.layers.batch_normalization(x1, training=is_train)
x1 = tf.maximum(alpha * x1, x1)
x2 = tf.layers.conv2d_transpose(x1, 256, 5, strides=2, padding='valid')
x2 = tf.layers.batch_normalization(x2, training=is_train)
x2 = tf.maximum(alpha * x2, x2)
x3 = tf.layers.conv2d_transpose(x2, 128, 5, strides=2, padding='same')
x3 = tf.layers.batch_normalization(x3, training=is_train)
x3 = tf.maximum(alpha * x3, x3)
logits = tf.layers.conv2d_transpose(x3, out_channel_dim, 5, strides=2, padding='same')
out = tf.tanh(logits)
return out
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
In [8]:
def model_loss(input_real, input_z, out_channel_dim):
"""
Get the loss for the discriminator and generator
:param input_real: Images from the real dataset
:param input_z: Z input
:param out_channel_dim: The number of channels in the output image
:return: A tuple of (discriminator loss, generator loss)
"""
# TODO: Implement Function
g_model = generator(input_z, out_channel_dim, is_train=True)
d_model_real, d_logits_real = discriminator(input_real, reuse=False)
d_model_fake, d_logits_fake = discriminator(g_model, reuse=True)
d_loss_real = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.ones_like(d_model_real)))
d_loss_fake = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.zeros_like(d_model_fake)))
g_loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake)))
d_loss = d_loss_real + d_loss_fake
return (d_loss, g_loss)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_loss(model_loss)
In [9]:
def model_opt(d_loss, g_loss, learning_rate, beta1):
"""
Get optimization operations
:param d_loss: Discriminator loss Tensor
:param g_loss: Generator loss Tensor
:param learning_rate: Learning Rate Placeholder
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:return: A tuple of (discriminator training operation, generator training operation)
"""
# TODO: Implement Function
vars = tf.trainable_variables()
d_vars = [var for var in vars if var.name.startswith('discriminator')]
g_vars = [var for var in vars if var.name.startswith('generator')]
all_update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
g_update_ops = [var for var in all_update_ops if var.name.startswith('generator')]
d_update_ops = [var for var in all_update_ops if var.name.startswith('discriminator')]
with tf.control_dependencies(d_update_ops):
d_train = tf.train.AdamOptimizer(learning_rate, beta1 = beta1).minimize(d_loss, var_list = d_vars)
with tf.control_dependencies(g_update_ops):
g_train = tf.train.AdamOptimizer(learning_rate, beta1 = beta1).minimize(g_loss, var_list = g_vars)
return d_train, g_train
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_opt(model_opt, tf)
In [10]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np
def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):
"""
Show example output for the generator
:param sess: TensorFlow session
:param n_images: Number of Images to display
:param input_z: Input Z Tensor
:param out_channel_dim: The number of channels in the output image
:param image_mode: The mode to use for images ("RGB" or "L")
"""
cmap = None if image_mode == 'RGB' else 'gray'
z_dim = input_z.get_shape().as_list()[-1]
example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])
samples = sess.run(
generator(input_z, out_channel_dim, False),
feed_dict={input_z: example_z})
images_grid = helper.images_square_grid(samples, image_mode)
pyplot.imshow(images_grid, cmap=cmap)
pyplot.show()
In [11]:
def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode):
"""
Train the GAN
:param epoch_count: Number of epochs
:param batch_size: Batch Size
:param z_dim: Z dimension
:param learning_rate: Learning Rate
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:param get_batches: Function to get batches
:param data_shape: Shape of the data
:param data_image_mode: The image mode to use for images ("RGB" or "L")
"""
# TODO: Build Model
# Inputs
input_real, input_z, lr = model_inputs(data_shape[1], data_shape[2], data_shape[3], z_dim)
# Loss
d_loss, g_loss = model_loss(input_real, input_z, data_shape[3])
# Optimizers
d_opt, g_opt = model_opt(d_loss, g_loss, learning_rate, beta1)
sample_z = np.random.uniform(-1, 1, size=(50, z_dim))
samples, losses = [], []
steps = 0
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch_i in range(epoch_count):
for batch_images in get_batches(batch_size):
# TODO: Train Model
steps += 1
batch_z = np.random.uniform(-1, 1, size=(batch_size, z_dim))
batch_images = batch_images * 2
_ = sess.run(d_opt, feed_dict={input_real:batch_images, input_z: batch_z, lr:learning_rate})
_ = sess.run(g_opt, feed_dict={input_z:batch_z, lr:learning_rate})
if steps % 10 == 0:
# At the end of each epoch, get the losses and print them out
train_loss_d = d_loss.eval({input_z: batch_z, input_real: batch_images})
train_loss_g = g_loss.eval({input_z: batch_z})
print("Epoch {}/{}...".format(epoch_i+1, epochs),
"Discriminator Loss: {:.4f}...".format(train_loss_d),
"Generator Loss: {:.4f}".format(train_loss_g))
losses.append((train_loss_d, train_loss_g))
if steps % 100 == 0:
gen_samples = sess.run(
generator(input_z, data_shape[3], is_train=False),
feed_dict={input_z: sample_z})
samples.append(gen_samples)
_ = show_generator_output(sess, 5, input_z, data_shape[3], data_image_mode)
In [ ]:
batch_size = 32
z_dim = 100
learning_rate = 0.0001
beta1 = 0.1
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 5
mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))
with tf.Graph().as_default():
train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,
mnist_dataset.shape, mnist_dataset.image_mode)
In [ ]: