def make_data_set():
ds = Dataset()
print("Datasets loaded.")
X_all = pad_vec_sequences(ds.X_all_vec_seq)
Y_all = ds.Y_all
#print (X_all.shape)
x_train, x_test, y_train, y_test = model_selection.train_test_split(X_all,Y_all,test_size=0.2)
y_train = pad_class_sequence(y_train, nb_classes)
y_test = pad_class_sequence(y_test, nb_classes)
y_test = np.array(y_test)
x_train = np.asarray(x_train)
x_train.ravel()
y_train = np.asarray(y_train)
y_train.ravel()
return x_train,y_train,x_test,y_test
import tensorflow as tf
#from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import os, sys
#sys.path.insert(0, 'utils')
from preprocessor import Dataset
dataset = Dataset('obj', '.jpg')
#data = dataset.nextBatch(64)
#mnist = input_data.read_data_sets('/home/sonar/PycharmProjects/generative-models-master/MNIST_data', one_hot=True)
mb_size = 64
Z_dim = 100
#X_dim = mnist.train.images.shape[1]
#y_dim = mnist.train.labels.shape[1]
X_dim = 784
y_dim = 2
#h_dim = 128
h_dim = 300
def xavier_init(size):
in_dim = size[0]
xavier_stddev = 1. / tf.sqrt(in_dim / 2.)
return tf.random_normal(shape=size, stddev=xavier_stddev)
""" Discriminator Net model """
import keras
from preprocessor import Dataset, pad_vec_sequences
from sklearn.model_selection import train_test_split
from keras.preprocessing import sequence
from keras.models import Sequential
from keras.models import Model
from keras.layers import Dense, Dropout, Embedding, LSTM, Input, merge, GRU, Activation
from keras.utils import np_utils, generic_utils
from keras.preprocessing.text import Tokenizer
import numpy as np
max_words = 1000
batch_size = 128
epochs = 100
ds = Dataset()
X_all = ds.X_all_sent
Y_all = ds.Y_all
x_train, x_test, y_train, y_test = train_test_split(X_all,
Y_all,
test_size=0.1,
random_state=42)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
num_classes = 3 + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('x_train shape:', x_train.shape)
def __init__(self, sess, input_height=108, input_width=108, crop=True,
batch_size=64, sample_num=64, output_height=64, output_width=64,
y_dim=None, z_dim=100, gf_dim=64, df_dim=64,
gfc_dim=1024, dfc_dim=1024, c_dim=1, dataset_name='default',
input_fname_pattern='*.jpg', checkpoint_dir=None, sample_dir=None, data_dir='./data'):
"""
Args:
sess: TensorFlow session
batch_size: The size of batch. Should be specified before training.
y_dim: (optional) Dimension of dim for y. [None]
z_dim: (optional) Dimension of dim for Z. [100]
gf_dim: (optional) Dimension of gen filters in first conv layer. [64]
df_dim: (optional) Dimension of discrim filters in first conv layer. [64]
gfc_dim: (optional) Dimension of gen units for for fully connected layer. [1024]
dfc_dim: (optional) Dimension of discrim units for fully connected layer. [1024]
c_dim: (optional) Dimension of image color. For grayscale input, set to 1. [3]
"""
self.sess = sess
self.crop = crop
self.dataset = Dataset('obj','.jpg')
self.batch_size = batch_size
self.sample_num = sample_num
self.input_height = input_height
self.input_width = input_width
self.output_height = output_height
self.output_width = output_width
self.y_dim = y_dim
self.z_dim = z_dim
self.gf_dim = gf_dim
self.df_dim = df_dim
self.gfc_dim = gfc_dim
self.dfc_dim = dfc_dim
self.c_dim = 1
# batch normalization : deals with poor initialization helps gradient flow
self.d_bn1 = batch_norm(name='d_bn1')
self.d_bn2 = batch_norm(name='d_bn2')
if not self.y_dim:
self.d_bn3 = batch_norm(name='d_bn3')
self.g_bn0 = batch_norm(name='g_bn0')
self.g_bn1 = batch_norm(name='g_bn1')
self.g_bn2 = batch_norm(name='g_bn2')
if not self.y_dim:
self.g_bn3 = batch_norm(name='g_bn3')
self.dataset_name = dataset_name
self.input_fname_pattern = input_fname_pattern
self.checkpoint_dir = checkpoint_dir
self.data_dir = data_dir
self.grayscale = (self.c_dim == 1)
self.build_model()
class DCGAN(object):
def __init__(self, sess, input_height=108, input_width=108, crop=True,
batch_size=64, sample_num=64, output_height=64, output_width=64,
y_dim=None, z_dim=100, gf_dim=64, df_dim=64,
gfc_dim=1024, dfc_dim=1024, c_dim=1, dataset_name='default',
input_fname_pattern='*.jpg', checkpoint_dir=None, sample_dir=None, data_dir='./data'):
"""
Args:
sess: TensorFlow session
batch_size: The size of batch. Should be specified before training.
y_dim: (optional) Dimension of dim for y. [None]
z_dim: (optional) Dimension of dim for Z. [100]
gf_dim: (optional) Dimension of gen filters in first conv layer. [64]
df_dim: (optional) Dimension of discrim filters in first conv layer. [64]
gfc_dim: (optional) Dimension of gen units for for fully connected layer. [1024]
dfc_dim: (optional) Dimension of discrim units for fully connected layer. [1024]
c_dim: (optional) Dimension of image color. For grayscale input, set to 1. [3]
"""
self.sess = sess
self.crop = crop
self.dataset = Dataset('obj','.jpg')
self.batch_size = batch_size
self.sample_num = sample_num
self.input_height = input_height
self.input_width = input_width
self.output_height = output_height
self.output_width = output_width
self.y_dim = y_dim
self.z_dim = z_dim
self.gf_dim = gf_dim
self.df_dim = df_dim
self.gfc_dim = gfc_dim
self.dfc_dim = dfc_dim
self.c_dim = 1
# batch normalization : deals with poor initialization helps gradient flow
self.d_bn1 = batch_norm(name='d_bn1')
self.d_bn2 = batch_norm(name='d_bn2')
if not self.y_dim:
self.d_bn3 = batch_norm(name='d_bn3')
self.g_bn0 = batch_norm(name='g_bn0')
self.g_bn1 = batch_norm(name='g_bn1')
self.g_bn2 = batch_norm(name='g_bn2')
if not self.y_dim:
self.g_bn3 = batch_norm(name='g_bn3')
self.dataset_name = dataset_name
self.input_fname_pattern = input_fname_pattern
self.checkpoint_dir = checkpoint_dir
self.data_dir = data_dir
self.grayscale = (self.c_dim == 1)
self.build_model()
def build_model(self):
if self.y_dim:
self.y = tf.placeholder(tf.float32, [self.batch_size, self.y_dim], name='y')
else:
self.y = None
if self.crop:
image_dims = [self.output_height, self.output_width, self.c_dim]
else:
image_dims = [self.input_height, self.input_width, self.c_dim]
self.inputs = tf.placeholder(
tf.float32, [self.batch_size] + image_dims, name='real_images')
inputs = self.inputs
self.z = tf.placeholder(
tf.float32, [None, self.z_dim], name='z')
self.z_sum = histogram_summary("z", self.z)
self.G = self.generator(self.z, self.y)
self.D, self.D_logits = self.discriminator(inputs, self.y, reuse=False)
self.sampler = self.sampler(self.z, self.y)
self.D_, self.D_logits_ = self.discriminator(self.G, self.y, reuse=True)
self.d_sum = histogram_summary("d", self.D)
self.d__sum = histogram_summary("d_", self.D_)
self.G_sum = image_summary("G", self.G)
def sigmoid_cross_entropy_with_logits(x, y):
try:
return tf.nn.sigmoid_cross_entropy_with_logits(logits=x, labels=y)
except:
return tf.nn.sigmoid_cross_entropy_with_logits(logits=x, targets=y)
self.d_loss_real = tf.reduce_mean(
sigmoid_cross_entropy_with_logits(self.D_logits, tf.ones_like(self.D)))
self.d_loss_fake = tf.reduce_mean(
sigmoid_cross_entropy_with_logits(self.D_logits_, tf.zeros_like(self.D_)))
self.g_loss = tf.reduce_mean(
sigmoid_cross_entropy_with_logits(self.D_logits_, tf.ones_like(self.D_)))
self.d_loss_real_sum = scalar_summary("d_loss_real", self.d_loss_real)
self.d_loss_fake_sum = scalar_summary("d_loss_fake", self.d_loss_fake)
self.d_loss = self.d_loss_real + self.d_loss_fake
self.g_loss_sum = scalar_summary("g_loss", self.g_loss)
self.d_loss_sum = scalar_summary("d_loss", self.d_loss)
t_vars = tf.trainable_variables()
self.d_vars = [var for var in t_vars if 'd_' in var.name]
self.g_vars = [var for var in t_vars if 'g_' in var.name]
self.saver = tf.train.Saver()
def train(self, config):
d_optim = tf.train.AdamOptimizer(config.learning_rate, beta1=config.beta1) \
.minimize(self.d_loss, var_list=self.d_vars)
g_optim = tf.train.AdamOptimizer(config.learning_rate, beta1=config.beta1) \
.minimize(self.g_loss, var_list=self.g_vars)
try:
tf.global_variables_initializer().run()
except:
tf.initialize_all_variables().run()
self.g_sum = merge_summary([self.z_sum, self.d__sum,
self.G_sum, self.d_loss_fake_sum, self.g_loss_sum])
self.d_sum = merge_summary(
[self.z_sum, self.d_sum, self.d_loss_real_sum, self.d_loss_sum])
self.writer = SummaryWriter("./logs", self.sess.graph)
sample_z = np.random.uniform(-1, 1, size=(self.sample_num, self.z_dim))
counter = 1
start_time = time.time()
could_load, checkpoint_counter = self.load(self.checkpoint_dir)
if could_load:
counter = checkpoint_counter
print(" [*] Load SUCCESS")
else:
print(" [!] Load failed...")
for epoch in xrange(1):
for counter in xrange(0, int(100000)):
if config.dataset == 'mnist':
#batch_images = self.data_X[idx * config.batch_size:(idx + 1) * config.batch_size]
#batch_labels = self.data_y[idx * config.batch_size:(idx + 1) * config.batch_size]
batch_labels, batch_images = self.dataset.nextBatch(self.batch_size)
# print batch_labels
# print()
batch_images = np.array(batch_images).reshape(-1, self.input_height, self.input_width, self.c_dim)
#cv2.imwrite('img.png',225* batch_images[0])
#cv2.waitKey()
else:
batch_files = self.data[idx * config.batch_size:(idx + 1) * config.batch_size]
batch = [
get_image(batch_file,
input_height=self.input_height,
input_width=self.input_width,
resize_height=self.output_height,
resize_width=self.output_width,
crop=self.crop,
grayscale=self.grayscale) for batch_file in batch_files]
if self.grayscale:
batch_images = np.array(batch).astype(np.float32)[:, :, :, None]
else:
batch_images = np.array(batch).astype(np.float32)
batch_z = np.random.uniform(-1, 1, [config.batch_size, self.z_dim]) \
.astype(np.float32)
# Update D network
_, summary_str = self.sess.run([d_optim, self.d_sum],
feed_dict={
self.inputs: batch_images,
self.z: batch_z,
self.y: batch_labels,
})
self.writer.add_summary(summary_str, counter)
_, summary_str = self.sess.run([d_optim, self.d_sum],
feed_dict={
self.inputs: batch_images,
self.z: batch_z,
self.y: batch_labels,
})
self.writer.add_summary(summary_str, counter)
_, summary_str = self.sess.run([d_optim, self.d_sum],
feed_dict={
self.inputs: batch_images,
self.z: batch_z,
self.y: batch_labels,
})
self.writer.add_summary(summary_str, counter)
# Update G network
if counter%5 == 1:
_, summary_str = self.sess.run([g_optim, self.g_sum],
feed_dict={
self.z: batch_z,
self.y: batch_labels,
})
self.writer.add_summary(summary_str, counter)
# Run g_optim twice to make sure that d_loss does not go to zero (different from paper)
#_, summary_str = self.sess.run([g_optim, self.g_sum],
#feed_dict={self.z: batch_z, self.y: batch_labels})
# self.writer.add_summary(summary_str, counter)
errD_fake = self.d_loss_fake.eval({
self.z: batch_z,
self.y: batch_labels
})
errD_real = self.d_loss_real.eval({
self.inputs: batch_images,
self.y: batch_labels
})
errG = self.g_loss.eval({
self.z: batch_z,
self.y: batch_labels
})
counter += 1
print("time: %4.4f, d_loss: %.8f, g_loss: %.8f" \
% (
time.time() - start_time, errD_fake + errD_real, errG))
if np.mod(counter, 200) == 1:
sample_l =np.zeros(shape=(64,2))
sample_l[:,0]= 1
samples, g_loss = self.sess.run(
[self.sampler, self.g_loss],
feed_dict={
self.z: sample_z,
#self.inputs: sample_inputs,
#self.y: sample_labels,
self.y: sample_l
}
)
save_images(samples, image_manifold_size(samples.shape[0]),
'./{}/train_{:02d}_{:04d}.png'.format(config.sample_dir, counter,counter))
print("[Sample] d_loss: %.8f, g_loss: %.8f" % (g_loss, g_loss))
if np.mod(counter, 500) == 2:
self.save(config.checkpoint_dir, counter)
def discriminator(self, image, y=None, reuse=False):
with tf.variable_scope("discriminator") as scope:
if reuse:
scope.reuse_variables()
if not self.y_dim:
h0 = lrelu(conv2d(image, self.df_dim, name='d_h0_conv'))
h1 = lrelu(self.d_bn1(conv2d(h0, self.df_dim * 2, name='d_h1_conv')))
h2 = lrelu(self.d_bn2(conv2d(h1, self.df_dim * 4, name='d_h2_conv')))
h3 = lrelu(self.d_bn3(conv2d(h2, self.df_dim * 8, name='d_h3_conv')))
h4 = linear(tf.reshape(h3, [self.batch_size, -1]), 1, 'd_h4_lin')
return tf.nn.sigmoid(h4), h4
else:
yb = tf.reshape(y, [self.batch_size, 1, 1, self.y_dim])
x = conv_cond_concat(image, yb)
h0 = lrelu(conv2d(x, self.c_dim + self.y_dim, name='d_h0_conv'))
h0 = conv_cond_concat(h0, yb)
h1 = lrelu(self.d_bn1(conv2d(h0, self.df_dim + self.y_dim, name='d_h1_conv')))
h1 = tf.reshape(h1, [self.batch_size, -1])
h1 = concat([h1, y], 1)
h2 = lrelu(self.d_bn2(linear(h1, self.dfc_dim, 'd_h2_lin')))
h2 = concat([h2, y], 1)
h3 = linear(h2, 1, 'd_h3_lin')
return tf.nn.sigmoid(h3), h3
def generator(self, z, y=None):
with tf.variable_scope("generator") as scope:
if not self.y_dim:
s_h, s_w = self.output_height, self.output_width
s_h2, s_w2 = conv_out_size_same(s_h, 2), conv_out_size_same(s_w, 2)
s_h4, s_w4 = conv_out_size_same(s_h2, 2), conv_out_size_same(s_w2, 2)
s_h8, s_w8 = conv_out_size_same(s_h4, 2), conv_out_size_same(s_w4, 2)
s_h16, s_w16 = conv_out_size_same(s_h8, 2), conv_out_size_same(s_w8, 2)
# project `z` and reshape
self.z_, self.h0_w, self.h0_b = linear(
z, self.gf_dim * 8 * s_h16 * s_w16, 'g_h0_lin', with_w=True)
self.h0 = tf.reshape(
self.z_, [-1, s_h16, s_w16, self.gf_dim * 8])
h0 = tf.nn.relu(self.g_bn0(self.h0))
self.h1, self.h1_w, self.h1_b = deconv2d(
h0, [self.batch_size, s_h8, s_w8, self.gf_dim * 4], name='g_h1', with_w=True)
h1 = tf.nn.relu(self.g_bn1(self.h1))
h2, self.h2_w, self.h2_b = deconv2d(
h1, [self.batch_size, s_h4, s_w4, self.gf_dim * 2], name='g_h2', with_w=True)
h2 = tf.nn.relu(self.g_bn2(h2))
h3, self.h3_w, self.h3_b = deconv2d(
h2, [self.batch_size, s_h2, s_w2, self.gf_dim * 1], name='g_h3', with_w=True)
h3 = tf.nn.relu(self.g_bn3(h3))
h4, self.h4_w, self.h4_b = deconv2d(
h3, [self.batch_size, s_h, s_w, self.c_dim], name='g_h4', with_w=True)
return tf.nn.tanh(h4)
else:
s_h, s_w = self.output_height, self.output_width
s_h2, s_h4 = int(s_h / 2), int(s_h / 4)
s_w2, s_w4 = int(s_w / 2), int(s_w / 4)
# yb = tf.expand_dims(tf.expand_dims(y, 1),2)
yb = tf.reshape(y, [self.batch_size, 1, 1, self.y_dim])
z = concat([z, y], 1)
h0 = tf.nn.relu(
self.g_bn0(linear(z, self.gfc_dim, 'g_h0_lin')))
h0 = concat([h0, y], 1)
h1 = tf.nn.relu(self.g_bn1(
linear(h0, self.gf_dim * 2 * s_h4 * s_w4, 'g_h1_lin')))
h1 = tf.reshape(h1, [self.batch_size, s_h4, s_w4, self.gf_dim * 2])
h1 = conv_cond_concat(h1, yb)
h2 = tf.nn.relu(self.g_bn2(deconv2d(h1,
[self.batch_size, s_h2, s_w2, self.gf_dim * 2], name='g_h2')))
h2 = conv_cond_concat(h2, yb)
return tf.nn.sigmoid(
deconv2d(h2, [self.batch_size, s_h, s_w, self.c_dim], name='g_h3'))
def sampler(self, z, y=None):
with tf.variable_scope("generator") as scope:
scope.reuse_variables()
if not self.y_dim:
s_h, s_w = self.output_height, self.output_width
s_h2, s_w2 = conv_out_size_same(s_h, 2), conv_out_size_same(s_w, 2)
s_h4, s_w4 = conv_out_size_same(s_h2, 2), conv_out_size_same(s_w2, 2)
s_h8, s_w8 = conv_out_size_same(s_h4, 2), conv_out_size_same(s_w4, 2)
s_h16, s_w16 = conv_out_size_same(s_h8, 2), conv_out_size_same(s_w8, 2)
# project `z` and reshape
h0 = tf.reshape(
linear(z, self.gf_dim * 8 * s_h16 * s_w16, 'g_h0_lin'),
[-1, s_h16, s_w16, self.gf_dim * 8])
h0 = tf.nn.relu(self.g_bn0(h0, train=False))
h1 = deconv2d(h0, [self.batch_size, s_h8, s_w8, self.gf_dim * 4], name='g_h1')
h1 = tf.nn.relu(self.g_bn1(h1, train=False))
h2 = deconv2d(h1, [self.batch_size, s_h4, s_w4, self.gf_dim * 2], name='g_h2')
h2 = tf.nn.relu(self.g_bn2(h2, train=False))
h3 = deconv2d(h2, [self.batch_size, s_h2, s_w2, self.gf_dim * 1], name='g_h3')
h3 = tf.nn.relu(self.g_bn3(h3, train=False))
h4 = deconv2d(h3, [self.batch_size, s_h, s_w, self.c_dim], name='g_h4')
return tf.nn.tanh(h4)
else:
s_h, s_w = self.output_height, self.output_width
s_h2, s_h4 = int(s_h / 2), int(s_h / 4)
s_w2, s_w4 = int(s_w / 2), int(s_w / 4)
# yb = tf.reshape(y, [-1, 1, 1, self.y_dim])
yb = tf.reshape(y, [self.batch_size, 1, 1, self.y_dim])
z = concat([z, y], 1)
h0 = tf.nn.relu(self.g_bn0(linear(z, self.gfc_dim, 'g_h0_lin'), train=False))
h0 = concat([h0, y], 1)
h1 = tf.nn.relu(self.g_bn1(
linear(h0, self.gf_dim * 2 * s_h4 * s_w4, 'g_h1_lin'), train=False))
h1 = tf.reshape(h1, [self.batch_size, s_h4, s_w4, self.gf_dim * 2])
h1 = conv_cond_concat(h1, yb)
h2 = tf.nn.relu(self.g_bn2(
deconv2d(h1, [self.batch_size, s_h2, s_w2, self.gf_dim * 2], name='g_h2'), train=False))
h2 = conv_cond_concat(h2, yb)
return tf.nn.sigmoid(deconv2d(h2, [self.batch_size, s_h, s_w, self.c_dim], name='g_h3'))
@property
def model_dir(self):
return "{}_{}_{}_{}".format(
self.dataset_name, self.batch_size,
self.output_height, self.output_width)
def save(self, checkpoint_dir, step):
model_name = "DCGAN.model"
checkpoint_dir = os.path.join(checkpoint_dir, self.model_dir)
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
self.saver.save(self.sess,
os.path.join(checkpoint_dir, model_name),
global_step=step)
def load(self, checkpoint_dir):
import re
print(" [*] Reading checkpoints...")
checkpoint_dir = os.path.join(checkpoint_dir, self.model_dir)
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
ckpt_name = os.path.basename(ckpt.model_checkpoint_path)
self.saver.restore(self.sess, os.path.join(checkpoint_dir, ckpt_name))
counter = int(next(re.finditer("(\d+)(?!.*\d)", ckpt_name)).group(0))
print(" [*] Success to read {}".format(ckpt_name))
return True, counter
else:
print(" [*] Failed to find a checkpoint")
return False, 0