def main():
start_time = time.time() # Clocking start
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# DRAGAN model
model = dragan.DRAGAN(s, batch_size=train_step['batch_size'])
# Initializing variables
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
# MNIST DataSet images
mnist = DataSet(ds_path="D:\\DataSet/mnist/").data
for global_step in range(saved_global_step, train_step['global_step']):
batch_x, _ = mnist.train.next_batch(model.batch_size)
batch_x_p = get_perturbed_images(batch_x)
batch_x = np.reshape(batch_x, [-1] + model.image_shape)
batch_x_p = np.reshape(batch_x_p, [-1] + model.image_shape)
batch_z = np.random.uniform(
-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.x_p: batch_x_p,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
},
)
if global_step % train_step['logging_interval'] == 0:
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x: batch_x,
model.x_p: batch_x_p,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Global Step %05d => " % global_step,
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
},
)
samples = np.reshape(samples, [-1] + model.image_shape)
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}.png'.format(
global_step)
# Generated image save
iu.save_images(samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir)
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# MNIST Dataset Load
mnist = DataSet(ds_path="D:\\DataSet/mnist/").data
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# CGAN Model
model = cgan.CGAN(s, batch_size=train_step['batch_size'])
# initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
sample_y = np.zeros(shape=[model.sample_num, model.n_classes])
for i in range(10):
sample_y[10 * i:10 * (i + 1), i] = 1
for global_step in range(saved_global_step, train_step['global_step']):
batch_x, batch_y = mnist.train.next_batch(model.batch_size)
batch_z = np.random.uniform(
-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.c: batch_y,
model.z: batch_z,
model.do_rate: 0.5,
},
)
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss],
feed_dict={
model.c: batch_y,
model.z: batch_z,
model.do_rate: 0.5,
})
# Logging
if global_step % train_step['logging_interval'] == 0:
batch_x, batch_y = mnist.test.next_batch(model.batch_size)
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x: batch_x,
model.c: batch_y,
model.z: batch_z,
model.do_rate: 0.5,
},
)
# Print Loss
print(
"[+] Step %08d => " % global_step,
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(model.g,
feed_dict={
model.c: sample_y,
model.z: sample_z,
model.do_rate: 0.0,
})
samples = np.reshape(samples, [-1, 28, 28, 1])
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir)
# Model save
model.saver.save(s, results['model'], global_step)
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # clocking start
# Dataset
dataset = DataSets(height=64,
width=64,
channel=3,
ds_path='D:/DataSets/pix2pix/',
ds_name="vangogh2photo")
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# DiscoGAN model
model = discogan.DiscoGAN(s)
# load model & graph & weight
global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
print("[+] global step : %s" % global_step, " successfully loaded")
else:
print('[-] No checkpoint file found')
# initializing variables
tf.global_variables_initializer().run()
d_overpowered = False # G loss > D loss * 2
for epoch in range(paras['epoch']):
for step in range(1000):
offset_a = (step * paras['batch_size']) % (
dataset.images_a.shape[0] - paras['batch_size'])
offset_b = (step * paras['batch_size']) % (
dataset.images_b.shape[0] - paras['batch_size'])
# batch data set
batch_a = dataset.images_a[offset_a:(offset_a +
paras['batch_size']), :]
batch_b = dataset.images_b[offset_b:(offset_b +
paras['batch_size']), :]
# update D network
if not d_overpowered:
s.run(model.d_op, feed_dict={model.A: batch_a})
# update G network
s.run(model.g_op, feed_dict={model.B: batch_b})
if epoch % paras['logging_interval'] == 0:
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.A: batch_a,
model.B: batch_b
})
# print loss
print(
"[+] Epoch %03d Step %04d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# update overpowered
d_overpowered = d_loss < g_loss / 2.0
# training G model with sample image and noise
ab_samples = s.run(model.G_s2b,
feed_dict={model.A: batch_a})
ba_samples = s.run(model.G_b2s,
feed_dict={model.B: batch_b})
# summary saver
model.writer.add_summary(summary, global_step=global_step)
# export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_ab_dir = results[
'sample_output'] + 'train_A_{0}_{1}.png'.format(
epoch, global_step)
sample_ba_dir = results[
'sample_output'] + 'train_B_{0}_{1}.png'.format(
epoch, global_step)
# Generated image save
iu.save_images(
ab_samples,
size=[sample_image_height, sample_image_width],
image_path=sample_ab_dir)
iu.save_images(
ba_samples,
size=[sample_image_height, sample_image_width],
image_path=sample_ba_dir)
# model save
model.saver.save(s,
results['model'],
global_step=global_step)
end_time = time.time() - start_time
# elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
if os.path.exists("./orig-model/"):
detect = True # There has to be pre-trained file
else:
detect = False
# AnoGAN Model
model = anogan.AnoGAN(detect=detect, use_label=False) # AnoGAN
# Initializing
s.run(tf.global_variables_initializer())
# loading CelebA DataSet
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="D:\\DataSet/CelebA/CelebA-64.h5",
ds_label_path="D:\\DataSet/CelebA/Anno/list_attr_celeba.txt",
# ds_image_path="D:\\DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="D:\\DataSet/CelebA/CelebA-128.h5",
save_type="to_h5",
use_img_scale=False,
# img_scale="-1,1"
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:16], inv_type='127'),
(16, 64, 64, 3))
iu.save_images(test_images,
size=[4, 4],
image_path=results['output'] + 'sample.png',
inv_type='127')
ds_iter = DataIterator(x=ds.images,
y=None,
batch_size=train_step['batch_size'],
label_off=True)
# To-Do
# Getting anomaly data
# Load model & Graph & Weights
if not detect or not os.path.exists("./ano-model/"):
ckpt = tf.train.get_checkpoint_state('./orig-model/')
else:
ckpt = tf.train.get_checkpoint_state('./ano-model/')
saved_global_step = 0
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epoch']):
for batch_images in ds_iter.iterate():
batch_x = np.reshape(batch_images,
[-1] + model.image_shape[1:])
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run([model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
})
if global_step % train_step['logging_step'] == 0:
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
# Summary
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
# Print loss
print(
"[+] Epoch %04d Step %07d =>" % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Summary saver
model.writer.add_summary(summary, epoch)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(model.g_test,
feed_dict={
model.z: sample_z,
})
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}_{1}.png'.format(
epoch, global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir)
# Model save
if not detect:
model.saver.save(s,
results['orig-model'],
global_step=global_step)
else:
model.saver.save(s,
results['ano-model'],
global_step=global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# CycleGAN Model
model = cyclegan.CycleGAN(s,
height=128,
width=128,
channel=3,
batch_size=train_step['batch_size'])
# Celeb-A DataSet images
ds = DataSet(height=128,
width=128,
channel=3,
ds_path="D:/DataSet/pix2pix/",
ds_name='vangogh2photo')
img_a = ds.images_a
img_b = ds.images_b
print("[*] image A shape : ", img_a.shape)
print("[*] image B shape : ", img_b.shape)
n_sample = model.sample_num
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir_a = results['output'] + 'valid_a.png'
sample_dir_b = results['output'] + 'valid_b.png'
sample_a, sample_b = img_a[:n_sample], img_b[:n_sample]
sample_a = np.reshape(sample_a, [-1] + model.image_shape[1:])
sample_b = np.reshape(sample_b, [-1] + model.image_shape[1:])
# Generated image save
iu.save_images(sample_a, [sample_image_height, sample_image_width],
sample_dir_a)
iu.save_images(sample_b, [sample_image_height, sample_image_width],
sample_dir_b)
print("[+] pre-processing elapsed time : {:.8f}s".format(time.time() -
start_time))
# Initializing
s.run(tf.global_variables_initializer())
global_step = 0
for epoch in range(train_step['epochs']):
# learning rate decay
lr_decay = 1.0
if epoch >= 100 and epoch % 10 == 0:
lr_decay = (train_step['epochs'] -
epoch) / (train_step['epochs'] / 2.0)
# re-implement DataIterator for multi-input
pointer = 0
num_images = min(ds.n_images_a, ds.n_images_b)
for i in range(num_images // train_step['batch_size']):
start = pointer
pointer += train_step['batch_size']
if pointer > num_images: # if ended 1 epoch
# Shuffle training DataSet
perm_a, perm_b = np.arange(ds.n_images_a), np.arange(
ds.n_images_b)
np.random.shuffle(perm_a)
np.random.shuffle(perm_b)
img_a, img_b = img_a[perm_a], img_a[perm_b]
start = 0
pointer = train_step['batch_size']
end = pointer
batch_a = np.reshape(img_a[start:end], model.image_shape)
batch_b = np.reshape(img_a[start:end], model.image_shape)
for _ in range(model.n_train_critic):
s.run(
model.d_op,
feed_dict={
model.a: batch_a,
model.b: batch_b,
model.lr_decay: lr_decay,
},
)
w, gp, g_loss, cycle_loss, _ = s.run(
[
model.w, model.gp, model.g_loss, model.cycle_loss,
model.g_op
],
feed_dict={
model.a: batch_a,
model.b: batch_b,
model.lr_decay: lr_decay,
},
)
if global_step % train_step['logging_step'] == 0:
# Summary
summary = s.run(
model.merged,
feed_dict={
model.a: batch_a,
model.b: batch_b,
model.lr_decay: lr_decay,
},
)
# Print loss
print(
"[+] Global Step %08d =>" % global_step,
" G loss : {:.8f}".format(g_loss),
" Cycle loss : {:.8f}".format(cycle_loss),
" w : {:.8f}".format(w),
" gp : {:.8f}".format(gp),
)
# Summary saver
model.writer.add_summary(summary, global_step=global_step)
# Training G model with sample image and noise
samples_a2b = s.run(
model.g_a2b,
feed_dict={
model.a: sample_a,
model.b: sample_b,
model.lr_decay: lr_decay,
},
)
samples_b2a = s.run(
model.g_b2a,
feed_dict={
model.a: sample_a,
model.b: sample_b,
model.lr_decay: lr_decay,
},
)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir_a2b = results[
'output'] + 'train_a2b_{0}.png'.format(global_step)
sample_dir_b2a = results[
'output'] + 'train_b2a_{0}.png'.format(global_step)
# Generated image save
iu.save_images(samples_a2b,
[sample_image_height, sample_image_width],
sample_dir_a2b)
iu.save_images(samples_b2a,
[sample_image_height, sample_image_width],
sample_dir_b2a)
# Model save
model.saver.save(s,
results['model'],
global_step=global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# pre-chosen
attr_labels = [
'Big_Nose',
'Black_Hair',
'Blond_Hair',
'Blurry',
'Brown_Hair',
'Bushy_Eyebrows',
'Chubby',
'Double_Chin',
'Eyeglasses',
'Gray_Hair',
]
# StarGAN Model
model = stargan.StarGAN(s, attr_labels=attr_labels) # StarGAN
# Initializing
s.run(tf.global_variables_initializer())
# loading CelebA DataSet
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="D:/DataSet/CelebA/CelebA-64.h5",
ds_label_path="D:/DataSet/CelebA/Anno/list_attr_celeba.txt",
# ds_image_path="D:/DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="D:/DataSet/CelebA/CelebA-64.h5",
save_type="to_h5",
use_img_scale=False,
img_scale="-1,1",
)
# x_A # Celeb-A
img_a = np.reshape(ds.images, [-1, 64, 64, 3])
attr_a = ds.labels
# x_B # Celeb-A # copied from x_A
# later it'll be replaced to another DataSet like RaFD, used in the paper
# but i can't find proper(good) DataSets, so i just do with single-domain (Celeb-A)
# img_b = img_a[:]
# attr_b = attr_a[:]
# ds_a_iter = DataIterator(img_a, attr_a, train_step['batch_size'])
# ds_b_iter = DataIterator(img_b, attr_b, train_step['batch_size'])
print("[+] pre-processing elapsed time : {:.8f}s".format(time.time() - start_time))
print("[*] image_A :", img_a.shape, " attribute A :", attr_a.shape)
global_step = 0
for epoch in range(train_step['epoch']):
# learning rate decay
lr_decay = 1.0
if epoch >= train_step['epoch']:
lr_decay = (train_step['epoch'] - epoch) / (train_step['epoch'] / 2.0)
# re-implement DataIterator for multi-input
pointer = 0
for i in range(ds.num_images // train_step['batch_size']):
start = pointer
pointer += train_step['batch_size']
if pointer > ds.num_images: # if ended 1 epoch
# Shuffle training DataSet
perm = np.arange(ds.num_images)
np.random.shuffle(perm)
# To-Do
# Getting Proper DataSet
img_a, img_b = img_a[perm], img_a[perm]
attr_a, attr_b = attr_a[perm], attr_a[perm]
start = 0
pointer = train_step['batch_size']
end = pointer
x_a, y_a = img_a[start:end], attr_a[start:end][:]
x_b, y_b = img_a[start:end], attr_a[start:end][:]
x_a = iu.transform(x_a, inv_type='127')
x_b = iu.transform(x_b, inv_type='127')
batch_a = ds.concat_data(x_a, y_a)
batch_b = ds.concat_data(x_b, y_b)
eps = np.random.rand(train_step['batch_size'], 1, 1, 1)
# Generate fake_B
fake_b = s.run(model.fake_B, feed_dict={model.x_A: batch_a})
# Update D network - 5 times
for _ in range(5):
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x_B: batch_b,
model.y_B: y_b,
model.fake_x_B: fake_b,
model.lr_decay: lr_decay,
model.epsilon: eps,
},
)
# Update G network - 1 time
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.x_A: batch_a,
model.x_B: batch_b,
model.y_B: y_b,
model.lr_decay: lr_decay,
model.epsilon: eps,
},
)
if global_step % train_step['logging_step'] == 0:
eps = np.random.rand(train_step['batch_size'], 1, 1, 1)
# Summary
samples, d_loss, g_loss, summary = s.run(
[model.fake_A, model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x_A: batch_a,
model.x_B: batch_b,
model.y_B: y_b,
model.fake_x_B: fake_b,
model.lr_decay: lr_decay,
model.epsilon: eps,
},
)
# Print loss
print(
"[+] Epoch %04d Step %07d =>" % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Summary saver
model.writer.add_summary(summary, epoch)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}_{1}.png'.format(epoch, global_step)
# Generated image save
iu.save_images(
samples, size=[sample_image_height, sample_image_width], image_path=sample_dir, inv_type='127'
)
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# UrbanSound8K Dataset load
mnist = MNISTDataSet().data
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# CoGAN Model
model = segan.SEGAN(s)
# Initializing
s.run(tf.global_variables_initializer())
sample_x, _ = mnist.test.next_batch(model.sample_num)
sample_y = np.zeros(shape=[model.sample_num, model.n_classes])
for i in range(10):
sample_y[10 * i:10 * (i + 1), i] = 1
for step in range(train_step['global_step']):
batch_x, batch_y = mnist.train.next_batch(model.batch_size)
batch_x = np.reshape(batch_x, model.image_shape)
batch_z = np.random.uniform(
-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x_1: batch_x,
model.x_2: batch_x,
# model.y: batch_y,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.x_1: batch_x,
model.x_2: batch_x,
# model.y: batch_y,
model.z: batch_z,
},
)
if step % train_step['logging_interval'] == 0:
batch_x, batch_y = mnist.train.next_batch(model.batch_size)
batch_x = np.reshape(batch_x, model.image_shape)
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x_1: batch_x,
model.x_2: batch_x,
# model.y: batch_y,
model.z: batch_z,
},
)
# Print loss
print("[+] Step %08d => " % step,
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss))
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
# Training G model with sample image and noise
samples_1 = s.run(
model.g_sample_1,
feed_dict={
# model.y: sample_y,
model.z: sample_z,
},
)
samples_2 = s.run(
model.g_sample_2,
feed_dict={
# model.y: sample_y,
model.z: sample_z,
},
)
samples_1 = np.reshape(samples_1, [-1] + model.image_shape[1:])
samples_2 = np.reshape(samples_2, [-1] + model.image_shape[1:])
# Summary saver
model.writer.add_summary(summary, global_step=step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir_1 = results['output'] + 'train_1_{:08d}.png'.format(
step)
sample_dir_2 = results['output'] + 'train_2_{:08d}.png'.format(
step)
# Generated image save
iu.save_images(samples_1,
size=[sample_image_height, sample_image_width],
image_path=sample_dir_1)
iu.save_images(samples_2,
size=[sample_image_height, sample_image_width],
image_path=sample_dir_2)
# Model save
model.saver.save(s, results['model'], global_step=step)
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
height, width, channel = 128, 128, 3
# loading CelebA DataSet
ds = DataSet(
height=height,
width=height,
channel=channel,
# ds_image_path="D:\\DataSet/CelebA/CelebA-%d.h5" % height,
ds_label_path=os.path.join(cfg.celeba_path, "Anno/list_attr_celeba.txt"),
ds_image_path=os.path.join(cfg.celeba_path, "Img/img_align_celeba/"),
ds_type="CelebA",
use_save=True,
save_file_name=os.path.join(cfg.celeba_path, "CelebA-%d.h5" % height),
save_type="to_h5",
use_img_scale=False,
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:16], inv_type='127'), (16, height, width, channel))
iu.save_images(test_images, size=[4, 4], image_path=os.path.join(cfg.output_path, "sample.png"), inv_type='127')
ds_iter = DataIterator(x=ds.images, y=None, batch_size=train_step['batch_size'], label_off=True)
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# BigGAN Model
model = biggan.BigGAN(s, height=height, width=width, channel=channel, batch_size=train_step['batch_size'])
# Initializing
s.run(tf.global_variables_initializer())
print("[*] Reading checkpoints...")
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state(cfg.model_path)
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step, " successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size) # recover n_epoch
ds_iter.pointer = saved_global_step % (ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epochs']):
for batch_x in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, (model.batch_size, model.height, model.width, model.channel))
batch_z = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
if global_step % train_step['logging_interval'] == 0:
summary = s.run(
model.merged,
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Epoch %04d Step %08d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g_test,
feed_dict={
model.z: sample_z,
},
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = os.path.join(cfg.output, 'train_{:08d}.png'.format(global_step))
# Generated image save
iu.save_images(
samples, size=[sample_image_height, sample_image_width], image_path=sample_dir, inv_type='127'
)
# Model save
model.saver.save(s, os.path.join(cfg.model_path, "BigGAN.ckpt"), global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# DualGAN Model
model = dualgan.DualGAN(s) # DualGAN
# Initializing
s.run(tf.global_variables_initializer())
# Celeb-A DataSet images
ds = DataSet(height=32, width=32, channel=3, ds_path="D:/DataSets/CelebA/", ds_type="CelebA").images
ds_iter = DataIterator(ds, None, train_step['batch_size'], label_off=True)
global_step = 0
for epoch in range(train_step['epoch']):
for batch_images in ds_iter.iterate():
batch_x = np.reshape(batch_images, [-1] + model.image_shape[1:])
batch_z = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
},
)
# Update k_t
_, k, m_global = s.run(
[model.k_update, model.k, model.m_global],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
if global_step % train_step['logging_step'] == 0:
batch_z = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Summary
_, k, m_global, d_loss, g_loss, summary = s.run(
[model.k_update, model.k, model.m_global, model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Epoch %04d Step %07d =>" % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
" k : {:.8f}".format(k),
" M : {:.8f}".format(m_global),
)
# Summary saver
model.writer.add_summary(summary, epoch)
# Training G model with sample image and noise
sample_z = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
},
)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}_{1}.png'.format(epoch, global_step)
# Generated image save
iu.save_images(samples, size=[sample_image_height, sample_image_width], image_path=sample_dir)
# Model save
model.saver.save(s, results['model'], global_step=global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Celeb-A DataSet images
ds = DataSet(
input_height=1024,
input_width=1024,
input_channel=3,
ds_type="CelebA-HQ",
ds_path="/home/zero/hdd/DataSet/CelebA-HQ",
).images
n_ds = 30000
dataset_iter = DataIterator(ds,
None,
train_step['batch_size'],
label_off=True)
rnd = random.randint(0, n_ds)
sample_x = ds[rnd]
sample_x = np.reshape(sample_x, [-1, 1024, 1024, 3])
# Export real image
valid_image_height = 1
valid_image_width = 1
sample_dir = results['output'] + 'valid.png'
# Generated image save
iu.save_images(sample_x,
size=[valid_image_height, valid_image_width],
image_path=sample_dir,
inv_type='127')
print("[+] sample image saved!")
print("[+] pre-processing took {:.8f}s".format(time.time() - start_time))
# GPU configure
gpu_config = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto(allow_soft_placement=True, gpu_options=gpu_config)
for idx, n_pg in enumerate(pg):
with tf.Session(config=config) as s:
pg_t = False if idx % 2 == 0 else True
# PGGAN Model
model = pggan.PGGAN(s, pg=n_pg, pg_t=pg_t) # PGGAN
# Initializing
s.run(tf.global_variables_initializer())
if not n_pg == 1 and not n_pg == 7:
if pg_t:
model.r_saver.restore(
s, results['model'] + '%d-%d.ckpt' % (idx, r_pg[idx]))
model.out_saver.restore(
s, results['model'] + '%d-%d.ckpt' % (idx, r_pg[idx]))
else:
model.saver.restore(
s, results['model'] + '%d-%d.ckpt' % (idx, r_pg[idx]))
global_step = 0
for epoch in range(train_step['epoch']):
# Later, adding n_critic for optimizing D net
for batch_images in dataset_iter.iterate():
batch_x = np.reshape(batch_images, (-1, 128, 128, 3))
batch_x = (batch_x + 1.0) * 127.5 # re-scaling to (0, 255)
batch_x = image_resize(batch_x, s=model.output_size)
batch_x = (batch_x / 127.5) - 1.0 # re-scaling to (-1, 1)
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
if pg_t and not pg == 0:
alpha = global_step / 32000.0
low_batch_x = zoom(batch_x, zoom=[1.0, 0.5, 0.5, 1.0])
low_batch_x = zoom(low_batch_x,
zoom=[1.0, 2.0, 2.0, 1.0])
batch_x = alpha * batch_x + (1.0 - alpha) * low_batch_x
# Update D network
_, d_loss = s.run([model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
})
# Update alpha_trans
s.run(model.alpha_trans_update,
feed_dict={model.step_pl: global_step})
if global_step % train_step['logging_step'] == 0:
gp, d_loss, g_loss, summary = s.run(
[
model.gp, model.d_loss, model.g_loss,
model.merged
],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Print loss
print(
"[+] PG %d Epoch %03d Step %07d =>" %
(n_pg, epoch, global_step),
" D loss : {:.6f}".format(d_loss),
" G loss : {:.6f}".format(g_loss),
" GP : {:.6f}".format(gp),
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(model.g,
feed_dict={
model.z: sample_z,
})
samples = np.clip(samples, -1, 1)
# Export image generated by model G
sample_image_height = 1
sample_image_width = 1
sample_dir = results[
'output'] + 'train_{0}.png'.format(global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127',
)
# Model save
model.saver.save(s,
results['model'] + '%d-%d.ckpt' %
(idx, n_pg),
global_step=global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
def main():
start_time = time.time() # Clocking start
# loading CelebA DataSet
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="D:/DataSet/CelebA/CelebA-64.h5",
ds_label_path="D:/DataSet/CelebA/Anno/list_attr_celeba.txt",
# ds_image_path="D:/DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="D:/DataSet/CelebA/CelebA-64.h5",
save_type="to_h5",
use_img_scale=False,
img_scale="-1,1",
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:100], inv_type='127'),
(100, 64, 64, 3))
iu.save_images(test_images,
size=[10, 10],
image_path=results['output'] + 'sample.png',
inv_type='127')
ds_iter = DataIterator(x=ds.images,
y=None,
batch_size=train_step['batch_size'],
label_off=True)
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# MAGAN Model
model = magan.MAGAN(s)
# Initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
n_steps = ds.num_images // model.batch_size # training set size
# Pre-Train
print("[*] pre-training - getting proper Margin")
margin = 0 # 3.0585415484215974
if margin == 0:
sum_d_loss = 0.0
for i in range(2):
for batch_x in ds_iter.iterate():
batch_x = np.reshape(
iu.transform(batch_x, inv_type='127'),
(model.batch_size, model.height, model.width,
model.channel),
)
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
_, d_real_loss = s.run(
[model.d_op, model.d_real_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
model.m: 0.0,
},
)
sum_d_loss += d_real_loss
print("[*] Epoch {:1d} Sum of d_real_loss : {:.8f}".format(
i + 1, sum_d_loss))
# Initial margin value
margin = sum_d_loss / n_steps
print("[+] Margin : {0}".format(margin))
old_margin = margin
s_g_0 = np.inf # Sg_0 = infinite
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epochs']):
s_d, s_g = 0.0, 0.0
for batch_x in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, (model.batch_size, model.height,
model.width, model.channel))
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss, d_real_loss = s.run(
[model.d_op, model.d_loss, model.d_real_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
model.m: margin,
},
)
# Update D real sample
s_d += np.sum(d_real_loss)
# Update G network
_, g_loss, d_fake_loss = s.run(
[model.g_op, model.g_loss, model.d_fake_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
model.m: margin,
},
)
# Update G fake sample
s_g += np.sum(d_fake_loss)
# Logging
if global_step % train_step['logging_interval'] == 0:
summary = s.run(
model.merged,
feed_dict={
model.x: batch_x,
model.z: batch_z,
model.m: margin,
},
)
# Print loss
print(
"[+] Epoch %03d Global Step %05d => " %
(epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
model.m: margin,
},
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
# Update margin
if s_d / n_steps < margin and s_d < s_g and s_g_0 <= s_g:
margin = s_d / n_steps
print("[*] Margin updated from {:8f} to {:8f}".format(
old_margin, margin))
old_margin = margin
s_g_0 = s_g
# Convergence Measure
e_d = s_d / n_steps
e_g = s_g / n_steps
l_ = e_d + np.abs(e_d - e_g)
print("[+] Epoch %03d " % epoch, " L : {:.8f}".format(l_))
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# MNIST Dataset load
mnist = DataSet(ds_path="D:/DataSet/mnist/").data
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# GAN Model
model = gan.GAN(s)
# Initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step, " successfully loaded")
else:
print('[-] No checkpoint file found')
d_loss = 0.0
d_overpowered = False
for global_step in range(saved_global_step, train_step['global_step']):
batch_x, _ = mnist.train.next_batch(model.batch_size)
batch_x = batch_x.reshape(-1, model.n_input)
batch_z = np.random.uniform(-1.0, 1.0, size=[model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
if not d_overpowered:
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
d_overpowered = d_loss < (g_loss / 2.0)
if global_step % train_step['logging_interval'] == 0:
batch_x, _ = mnist.test.next_batch(model.batch_size)
batch_z = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
d_overpowered = d_loss < (g_loss / 2.0)
# Print loss
print(
"[+] Step %08d => " % global_step,
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
},
)
samples = np.reshape(samples, [-1, model.height, model.width, model.channel])
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(global_step)
# Generated image save
iu.save_images(samples, size=[sample_image_height, sample_image_width], image_path=sample_dir)
# Model save
model.saver.save(s, results['model'], global_step)
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time)) # took about 370s on my machine
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Training, test data set
ds = DataSet(height=32, width=32, channel=3, ds_path='D:\\DataSet/cifar/cifar-10-batches-py/', ds_name='cifar-10')
ds_iter = DataIterator(ds.train_images, ds.train_labels, train_step['batch_size'])
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# LAPGAN model
model = lapgan.LAPGAN(s, batch_size=train_step['batch_size'])
# Initializing variables
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step, " successfully loaded")
else:
print('[-] No checkpoint file found')
sample_y = np.zeros(shape=[model.sample_num, model.n_classes])
for i in range(10):
sample_y[10 * i : 10 * (i + 1), i] = 1
global_step = saved_global_step
start_epoch = global_step // (len(ds.train_images) // model.batch_size) # recover n_epoch
ds_iter.pointer = saved_global_step % (len(ds.train_images) // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epoch']):
for batch_images, batch_labels in ds_iter.iterate():
batch_x = iu.transform(batch_images, inv_type='127')
z = []
for i in range(3):
z.append(np.random.uniform(-1.0, 1.0, [train_step['batch_size'], model.z_noises[i]]))
# Update D/G networks
(
img_fake,
img_coarse,
d_loss_1,
g_loss_1,
_,
_,
_,
d_loss_2,
g_loss_2,
_,
_,
d_loss_3,
g_loss_3,
_,
_,
_,
_,
_,
_,
) = s.run(
[
model.g[0],
model.x1_coarse,
model.d_loss[0],
model.g_loss[0],
model.x2_fine,
model.g[1],
model.x2_coarse,
model.d_loss[1],
model.g_loss[1],
model.x3_fine,
model.g[2],
model.d_loss[2],
model.g_loss[2],
model.d_op[0],
model.g_op[0],
model.d_op[1],
model.g_op[1],
model.d_op[2],
model.g_op[2],
],
feed_dict={
model.x1_fine: batch_x, # images
model.y: batch_labels, # classes
model.z[0]: z[0],
model.z[1]: z[1],
model.z[2]: z[2], # z-noises
model.do_rate: 0.5,
},
)
# Logging
if global_step % train_step['logging_interval'] == 0:
batch_x = ds.test_images[np.random.randint(0, len(ds.test_images), model.sample_num)]
batch_x = iu.transform(batch_x, inv_type='127')
z = []
for i in range(3):
z.append(np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_noises[i]]))
# Update D/G networks
(
img_fake,
img_coarse,
d_loss_1,
g_loss_1,
_,
_,
_,
d_loss_2,
g_loss_2,
_,
_,
d_loss_3,
g_loss_3,
_,
_,
_,
_,
_,
_,
summary,
) = s.run(
[
model.g[0],
model.x1_coarse,
model.d_loss[0],
model.g_loss[0],
model.x2_fine,
model.g[1],
model.x2_coarse,
model.d_loss[1],
model.g_loss[1],
model.x3_fine,
model.g[2],
model.d_loss[2],
model.g_loss[2],
model.d_op[0],
model.g_op[0],
model.d_op[1],
model.g_op[1],
model.d_op[2],
model.g_op[2],
model.merged,
],
feed_dict={
model.x1_fine: batch_x, # images
model.y: sample_y, # classes
model.z[0]: z[0],
model.z[1]: z[1],
model.z[2]: z[2], # z-noises
model.do_rate: 0.0,
},
)
# Print loss
d_loss = (d_loss_1 + d_loss_2 + d_loss_3) / 3.0
g_loss = (g_loss_1 + g_loss_2 + g_loss_3) / 3.0
print(
"[+] Epoch %03d Step %05d => " % (epoch, global_step),
" Avg D loss : {:.8f}".format(d_loss),
" Avg G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
samples = img_fake + img_coarse
# Summary saver
model.writer.add_summary(summary, global_step) # time saving
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}.png'.format(global_step)
# Generated image save
iu.save_images(
samples, size=[sample_image_height, sample_image_width], image_path=sample_dir, inv_type='127'
)
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# loading CelebA DataSet
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="/home/zero/hdd/DataSet/CelebA/CelebA-64.h5",
ds_label_path="/home/zero/hdd/DataSet/CelebA/Anno/list_attr_celeba.txt",
# ds_image_path="/home/zero/hdd/DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="/home/zero/hdd/DataSet/CelebA/CelebA-64.h5",
save_type="to_h5",
use_img_scale=False,
# img_scale="-1,1"
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:16], inv_type='127'),
(16, 64, 64, 3))
iu.save_images(test_images,
size=[4, 4],
image_path=results['output'] + 'sample.png',
inv_type='127')
ds_iter = DataIterator(x=ds.images,
y=None,
batch_size=train_step['batch_size'],
label_off=True)
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# EBGAN Model
model = ebgan.EBGAN(
s, enable_pull_away=True) # using pull away loss # EBGAN-PT
# Initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epochs']):
for batch_x in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, (model.batch_size, model.height,
model.width, model.channel))
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
},
)
# Logging
if global_step % train_step['logging_interval'] == 0:
summary = s.run(
model.merged,
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Epoch %02d Step %08d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
},
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Loading Cifar-10 DataSet
ds = DataSet(height=32,
width=32,
channel=3,
ds_path="D:/DataSet/cifar/cifar-10-batches-py/",
ds_name='cifar-10')
ds_iter = DataIterator(
x=iu.transform(ds.train_images, '127'),
y=ds.train_labels,
batch_size=train_step['batch_size'],
label_off=False
) # using label # maybe someday, i'll change this param's name
# Generated image save
test_images = iu.transform(ds.test_images[:100], inv_type='127')
iu.save_images(test_images,
size=[10, 10],
image_path=results['output'] + 'sample.png',
inv_type='127')
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# ACGAN Model
model = acgan.ACGAN(s,
batch_size=train_step['batch_size'],
n_classes=ds.n_classes)
# Initializing
s.run(tf.global_variables_initializer())
sample_y = np.zeros(shape=[model.sample_num, model.n_classes])
for i in range(10):
sample_y[10 * i:10 * (i + 1), i] = 1
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (len(ds.train_images) // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
len(ds.train_images) // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epochs']):
for batch_x, batch_y in ds_iter.iterate():
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.y: batch_y,
model.z: batch_z,
},
)
# Update G/C networks
_, g_loss, _, c_loss = s.run(
[model.g_op, model.g_loss, model.c_op, model.c_loss],
feed_dict={
model.x: batch_x,
model.y: batch_y,
model.z: batch_z,
},
)
if global_step % train_step['logging_interval'] == 0:
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
d_loss, g_loss, c_loss, summary = s.run(
[
model.d_loss, model.g_loss, model.c_loss,
model.merged
],
feed_dict={
model.x: batch_x,
model.y: batch_y,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Epoch %04d Step %08d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
" C loss : {:.8f}".format(c_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.y: sample_y,
model.z: sample_z,
},
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# loading CelebA DataSet
labels = [
'Black_Hair',
'Blond_Hair',
'Blurry',
'Eyeglasses',
'Gray_Hair',
'Male',
'Smiling',
'Wavy_Hair',
'Wearing_Hat',
'Young',
]
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="/home/zero/hdd/DataSet/CelebA/CelebA-64.h5",
ds_label_path="/home/zero/hdd/DataSet/CelebA/Anno/list_attr_celeba.txt",
attr_labels=labels,
# ds_image_path="D:\\DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="D:\\DataSet/CelebA/CelebA-64.h5",
save_type="to_h5",
use_img_scale=False,
# img_scale="-1,1"
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:16], inv_type='127'),
(16, 64, 64, 3))
iu.save_images(test_images,
size=[4, 4],
image_path=results['output'] + 'sample.png',
inv_type='127')
ds_iter = DataIterator(x=ds.images,
y=ds.labels,
batch_size=train_step['batch_size'],
label_off=False)
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# InfoGAN Model
model = infogan.InfoGAN(s,
height=64,
width=64,
channel=3,
batch_size=train_step['batch_size'],
n_categories=len(ds.labels))
# fixed z-noise
sample_z = np.random.uniform(
-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
# Initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %s" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epochs']):
for batch_x, batch_y in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, (model.batch_size, model.height,
model.width, model.channel))
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
batch_z_con = gen_continuous(model.batch_size,
model.n_continous_factor)
batch_z_cat = gen_category(model.batch_size,
model.n_categories)
batch_c = np.concatenate((batch_z_con, batch_z_cat), axis=1)
# Update D network
_, d_loss = s.run([model.d_op, model.d_loss],
feed_dict={
model.c: batch_c,
model.x: batch_x,
model.z: batch_z,
})
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss],
feed_dict={
model.c: batch_c,
model.x: batch_x,
model.z: batch_z,
})
# Logging
if global_step % train_step['logging_interval'] == 0:
summary = s.run(model.merged,
feed_dict={
model.c: batch_c,
model.x: batch_x,
model.z: batch_z,
})
# Print loss
print(
"[+] Epoch %02d Step %08d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z_con = np.zeros(
(model.sample_num, model.n_continous_factor))
for i in range(10):
sample_z_con[10 * i:10 * (i + 1),
0] = np.linspace(-2, 2, 10)
sample_z_cat = np.zeros(
(model.sample_num, model.n_categories))
for i in range(10):
sample_z_cat[10 * i:10 * (i + 1), i] = 1
sample_c = np.concatenate((sample_z_con, sample_z_cat),
axis=1)
samples = s.run(model.g,
feed_dict={
model.c: sample_c,
model.z: sample_z,
})
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Div2K - Track 1: Bicubic downscaling - x4 DataSet load
"""
ds = DataSet(ds_path="/home/zero/hdd/DataSet/DIV2K/",
ds_name="X4",
use_save=True,
save_type="to_h5",
save_file_name="/home/zero/hdd/DataSet/DIV2K/DIV2K",
use_img_scale=True)
"""
ds = DataSet(
ds_hr_path="/home/zero/hdd/DataSet/DIV2K/DIV2K-hr.h5",
ds_lr_path="/home/zero/hdd/DataSet/DIV2K/DIV2K-lr.h5",
use_img_scale=True,
)
hr, lr = ds.hr_images, ds.lr_images
print("[+] Loaded HR image ", hr.shape)
print("[+] Loaded LR image ", lr.shape)
# GPU configure
gpu_config = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto(allow_soft_placement=True,
log_device_placement=False,
gpu_options=gpu_config)
with tf.Session(config=config) as s:
with tf.device("/gpu:1"): # Change
# SRGAN Model
model = srgan.SRGAN(s,
batch_size=train_step['batch_size'],
use_vgg19=False)
# Initializing
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % global_step, " successfully loaded")
else:
global_step = 0
print('[-] No checkpoint file found')
start_epoch = global_step // (ds.n_images // train_step['batch_size'])
rnd = np.random.randint(0, ds.n_images)
sample_x_hr, sample_x_lr = hr[rnd], lr[rnd]
sample_x_hr, sample_x_lr = (
np.reshape(sample_x_hr, [1] + model.hr_image_shape[1:]),
np.reshape(sample_x_lr, [1] + model.lr_image_shape[1:]),
)
# Export real image
# valid_image_height = model.sample_size
# valid_image_width = model.sample_size
sample_hr_dir, sample_lr_dir = results[
'output'] + 'valid_hr.png', results['output'] + 'valid_lr.png'
# Generated image save
iu.save_images(sample_x_hr,
size=[1, 1],
image_path=sample_hr_dir,
inv_type='127')
iu.save_images(sample_x_lr,
size=[1, 1],
image_path=sample_lr_dir,
inv_type='127')
learning_rate = 1e-4
for epoch in range(start_epoch, train_step['train_epochs']):
pointer = 0
for i in range(ds.n_images // train_step['batch_size']):
start = pointer
pointer += train_step['batch_size']
if pointer > ds.n_images: # if 1 epoch is ended
# Shuffle training DataSet
perm = np.arange(ds.n_images)
np.random.shuffle(perm)
hr, lr = hr[perm], lr[perm]
start = 0
pointer = train_step['batch_size']
end = pointer
batch_x_hr, batch_x_lr = hr[start:end], lr[start:end]
# reshape
batch_x_hr = np.reshape(batch_x_hr,
[train_step['batch_size']] +
model.hr_image_shape[1:])
batch_x_lr = np.reshape(batch_x_lr,
[train_step['batch_size']] +
model.lr_image_shape[1:])
# Update Only G network
d_loss, g_loss, g_init_loss = 0.0, 0.0, 0.0
if epoch <= train_step['init_epochs']:
_, g_init_loss = s.run(
[model.g_init_op, model.g_cnt_loss],
feed_dict={
model.x_hr: batch_x_hr,
model.x_lr: batch_x_lr,
model.lr: learning_rate,
},
)
# Update G/D network
else:
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x_hr: batch_x_hr,
model.x_lr: batch_x_lr,
model.lr: learning_rate,
},
)
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.x_hr: batch_x_hr,
model.x_lr: batch_x_lr,
model.lr: learning_rate,
},
)
if i % train_step['logging_interval'] == 0:
# Print loss
if epoch <= train_step['init_epochs']:
print(
"[+] Epoch %04d Step %08d => " %
(epoch, global_step),
" MSE loss : {:.8f}".format(g_init_loss),
)
else:
print(
"[+] Epoch %04d Step %08d => " %
(epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
summary = s.run(
model.merged,
feed_dict={
model.x_hr: batch_x_hr,
model.x_lr: batch_x_lr,
model.lr: learning_rate,
},
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Training G model with sample image and noise
sample_x_lr = np.reshape(sample_x_lr, [model.sample_num] +
model.lr_image_shape[1:])
samples = s.run(
model.g,
feed_dict={
model.x_lr: sample_x_lr,
model.lr: learning_rate,
},
)
# Export image generated by model G
# sample_image_height = model.output_height
# sample_image_width = model.output_width
sample_dir = results['output'] + 'train_{:08d}.png'.format(
global_step)
# Generated image save
iu.save_images(samples,
size=[1, 1],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s, results['model'], global_step)
# Learning Rate update
if epoch and epoch % model.lr_update_epoch == 0:
learning_rate *= model.lr_decay_rate
learning_rate = max(learning_rate, model.lr_low_boundary)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Training, Test data set
# loading Cifar DataSet
ds = DataSet(height=32, width=32, channel=3, ds_path='D:\\DataSet/cifar/cifar-10-batches-py/', ds_name='cifar-10')
# saving sample images
test_images = np.reshape(iu.transform(ds.test_images[:16], inv_type='127'), (16, 32, 32, 3))
iu.save_images(test_images, size=[4, 4], image_path=results['output'] + 'sample.png', inv_type='127')
ds_iter = DataIterator(x=ds.train_images, y=None, batch_size=train_step['batch_size'], label_off=True)
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# GAN Model
model = lsgan.LSGAN(s, train_step['batch_size'])
# Initializing variables
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step, " successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (len(ds.train_images) // model.batch_size)
ds_iter.pointer = saved_global_step % (len(ds.train_images) // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epoch']):
for batch_x in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, [-1] + model.image_shape[1:])
batch_z = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run([model.d_op, model.d_loss], feed_dict={model.x: batch_x, model.z: batch_z})
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss], feed_dict={model.x: batch_x, model.z: batch_z})
# Logging
if global_step % train_step['logging_interval'] == 0:
d_loss, g_loss, summary = s.run(
[model.d_loss, model.g_loss, model.merged], feed_dict={model.x: batch_x, model.z: batch_z}
)
# Print loss
print(
"[+] Epoch %02d Step %08d => " % (epoch, global_step),
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(model.g, feed_dict={model.z: sample_z,})
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(global_step)
# Generated image save
iu.save_images(
samples, size=[sample_image_height, sample_image_width], image_path=sample_dir, inv_type='127'
)
# Model save
model.saver.save(s, results['model'], global_step)
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# Loading MNIST DataSet
mnist = DataSet(ds_path="D:\\DataSet/mnist/").data
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
idx = 1
divergences = [
'GAN',
'KL',
'Reverse-KL',
'JS',
'JS-Weighted',
'Squared-Hellinger',
'Pearson',
'Neyman',
'Jeffrey',
'Total-Variation',
]
assert 0 <= idx < len(divergences)
results['output'] += '%s/' % divergences[idx]
results['model'] += '%s/fGAN-model.ckpt' % divergences[idx]
with tf.Session(config=config) as s:
# f-GAN model
model = fgan.FGAN(s,
batch_size=train_step['batch_size'],
divergence_method=divergences[idx],
use_tricky_g_loss=True)
# Initializing variables
s.run(tf.global_variables_initializer())
# Load model & Graph & Weights
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/%s/' % divergences[idx])
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
for global_step in range(saved_global_step,
train_step['global_steps']):
batch_x, _ = mnist.train.next_batch(model.batch_size)
batch_z = np.random.uniform(
-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run([model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
# Update G network
_, g_loss = s.run([model.g_op, model.g_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
if global_step % train_step['logging_interval'] == 0:
summary = s.run(model.merged,
feed_dict={
model.x: batch_x,
model.z: batch_z,
})
# Print loss
print(
"[+] Global step %06d => " % global_step,
" D loss : {:.8f}".format(d_loss),
" G loss : {:.8f}".format(g_loss),
)
# Training G model with sample image and noise
sample_z = np.random.uniform(-1.0, 1.0,
[model.sample_num, model.z_dim])
samples = s.run(model.g, feed_dict={
model.z: sample_z,
})
samples = np.reshape(samples, (-1, 28, 28, 1))
# Summary saver
model.writer.add_summary(summary, global_step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}.png'.format(
global_step)
# Generated image save
iu.save_images(samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='255')
# Model save
model.saver.save(s, results['model'], global_step)
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# MNIST Dataset load
mnist = DataSet(ds_path="./").data
# GPU configure
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as s:
# SGAN Model
model = sgan.SGAN(s)
# Initializing
s.run(tf.global_variables_initializer())
sample_x, sample_y = mnist.test.next_batch(model.sample_num)
# sample_x = np.reshape(sample_x, [model.sample_num, model.n_input])
d_overpowered = False
for step in range(train_step['global_step']):
batch_x, batch_y = mnist.train.next_batch(model.batch_size)
# batch_x = np.reshape(batch_x, [model.batch_size, model.n_input])
batch_z_0 = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
batch_z_1 = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
if not d_overpowered:
_, d_0_loss, _, _ = s.run(
[model.d_0_op, model.d_0_loss, model.d_1_op, model.d_1_loss],
feed_dict={model.x: batch_x, model.y: batch_y, model.z_1: batch_z_1, model.z_0: batch_z_0,},
)
# Update G network
_, g_0_loss, _, _ = s.run(
[model.g_0_op, model.g_0_loss, model.g_1_op, model.g_1_loss],
feed_dict={model.x: batch_x, model.y: batch_y, model.z_1: batch_z_1, model.z_0: batch_z_0,},
)
d_overpowered = d_0_loss < g_0_loss / 2
if step % train_step['logging_interval'] == 0:
batch_x, batch_y = mnist.train.next_batch(model.batch_size)
# batch_x = np.reshape(batch_x, [model.batch_size, model.n_input])
batch_z_0 = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
batch_z_1 = np.random.uniform(-1.0, 1.0, [model.batch_size, model.z_dim]).astype(np.float32)
d_0_loss, _, g_0_loss, _, summary = s.run(
[model.d_0_loss, model.d_1_loss, model.g_0_loss, model.g_1_loss, model.merged],
feed_dict={model.x: batch_x, model.y: batch_y, model.z_1: batch_z_1, model.z_0: batch_z_0,},
)
d_overpowered = d_0_loss < g_0_loss / 2
# Print loss
print(
"[+] Step %08d => " % step, " D loss : {:.8f}".format(d_0_loss), " G loss : {:.8f}".format(g_0_loss)
)
# Training G model with sample image and noise
sample_z_0 = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
sample_z_1 = np.random.uniform(-1.0, 1.0, [model.sample_num, model.z_dim]).astype(np.float32)
_, samples = s.run(
[model.g_1, model.g_0], feed_dict={model.y: sample_y, model.z_1: sample_z_1, model.z_0: sample_z_0,}
)
samples = np.reshape(samples, [model.batch_size] + model.image_shape)
# Summary saver
model.writer.add_summary(summary, step)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{:08d}.png'.format(step)
# Generated image save
iu.save_images(samples, size=[sample_image_height, sample_image_width], image_path=sample_dir)
# Model save
model.saver.save(s, results['model'], global_step=step)
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
def main():
start_time = time.time() # Clocking start
# loading CelebA DataSet
ds = DataSet(
height=64,
width=64,
channel=3,
ds_image_path="/home/zero/hdd/DataSet/CelebA/CelebA-64.h5",
ds_label_path="/home/zero/hdd/DataSet/CelebA/Anno/list_attr_celeba.txt",
# ds_image_path="/home/zero/hdd/DataSet/CelebA/Img/img_align_celeba/",
ds_type="CelebA",
use_save=False,
save_file_name="/home/zero/hdd/DataSet/CelebA/CelebA-64.h5",
save_type="to_h5",
use_img_scale=False,
# img_scale="-1,1"
)
# saving sample images
test_images = np.reshape(iu.transform(ds.images[:100], inv_type='127'),
(100, 64, 64, 3))
iu.save_images(test_images,
size=[10, 10],
image_path=results['output'] + 'sample.png',
inv_type='127')
ds_iter = DataIterator(x=ds.images,
y=None,
batch_size=train_step['batch_size'],
label_off=True)
# GPU configure
gpu_config = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto(allow_soft_placement=True, gpu_options=gpu_config)
with tf.Session(config=config) as s:
# BEGAN Model
model = began.BEGAN(s, batch_size=train_step['batch_size'],
gamma=0.5) # BEGAN
# Initializing
s.run(tf.global_variables_initializer())
print("[*] Reading checkpoints...")
saved_global_step = 0
ckpt = tf.train.get_checkpoint_state('./model/')
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
model.saver.restore(s, ckpt.model_checkpoint_path)
saved_global_step = int(
ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
print("[+] global step : %d" % saved_global_step,
" successfully loaded")
else:
print('[-] No checkpoint file found')
global_step = saved_global_step
start_epoch = global_step // (ds.num_images // model.batch_size
) # recover n_epoch
ds_iter.pointer = saved_global_step % (
ds.num_images // model.batch_size) # recover n_iter
for epoch in range(start_epoch, train_step['epoch']):
for batch_x in ds_iter.iterate():
batch_x = iu.transform(batch_x, inv_type='127')
batch_x = np.reshape(batch_x, (model.batch_size, model.height,
model.width, model.channel))
batch_z = np.random.uniform(
-1.0, 1.0,
[model.batch_size, model.z_dim]).astype(np.float32)
# Update D network
_, d_loss = s.run(
[model.d_op, model.d_loss],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Update G network
_, g_loss = s.run(
[model.g_op, model.g_loss],
feed_dict={
model.z: batch_z,
},
)
# Update k_t
_, k, m_global = s.run(
[model.k_update, model.k, model.m_global],
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
if global_step % train_step['logging_step'] == 0:
summary = s.run(
model.merged,
feed_dict={
model.x: batch_x,
model.z: batch_z,
},
)
# Print loss
print(
"[+] Epoch %03d Step %07d =>" % (epoch, global_step),
" D loss : {:.6f}".format(d_loss),
" G loss : {:.6f}".format(g_loss),
" k : {:.6f}".format(k),
" M : {:.6f}".format(m_global),
)
# Summary saver
model.writer.add_summary(summary, global_step)
# Training G model with sample image and noise
sample_z = np.random.uniform(
-1.0, 1.0,
[model.sample_num, model.z_dim]).astype(np.float32)
samples = s.run(
model.g,
feed_dict={
model.z: sample_z,
},
)
# Export image generated by model G
sample_image_height = model.sample_size
sample_image_width = model.sample_size
sample_dir = results['output'] + 'train_{0}.png'.format(
global_step)
# Generated image save
iu.save_images(
samples,
size=[sample_image_height, sample_image_width],
image_path=sample_dir,
inv_type='127')
# Model save
model.saver.save(s,
results['model'],
global_step=global_step)
# Learning Rate update
if global_step and global_step % model.lr_update_step == 0:
s.run([model.g_lr_update, model.d_lr_update])
global_step += 1
end_time = time.time() - start_time # Clocking end
# Elapsed time
print("[+] Elapsed time {:.8f}s".format(end_time))
# Close tf.Session
s.close()
