def plot_original_data(filename="real_data"): try: os.mkdir(args.plot_dir) except: pass images = load_rgb_images(args.image_dir) x = sample_from_data(images, 100) x = (x + 1.0) / 2.0 tile_rgb_images(x.transpose(0, 2, 3, 1), dir=args.plot_dir, filename=filename)
def plot_original_data(filename="data"): try: os.mkdir(args.plot_dir) except: pass images = load_rgb_images(args.image_dir) x_true = sample_from_data(images, 100) x_true = (x_true + 1.0) / 2.0 visualizer.tile_rgb_images(x_true.transpose(0, 2, 3, 1), dir=args.plot_dir, filename=filename)
def main():
# load MNIST images
images = load_rgb_images(args.image_dir)
# config
config_energy_model = to_object(params_energy_model["config"])
config_generative_model = to_object(params_generative_model["config"])
# settings
max_epoch = 1000
n_trains_per_epoch = 500
batchsize_positive = 128
batchsize_negative = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# init weightnorm layers
if config_energy_model.use_weightnorm:
print "initializing weight normalization layers of the energy model ..."
x_positive = sample_from_data(images, batchsize_positive * 5)
ddgm.compute_energy(x_positive)
if config_generative_model.use_weightnorm:
print "initializing weight normalization layers of the generative model ..."
x_negative = ddgm.generate_x(batchsize_negative * 5)
progress = Progress()
for epoch in xrange(1, max_epoch):
progress.start_epoch(epoch, max_epoch)
sum_energy_positive = 0
sum_energy_negative = 0
sum_loss = 0
sum_kld = 0
for t in xrange(n_trains_per_epoch):
# sample from data distribution
x_positive = sample_from_data(images, batchsize_positive)
# sample from generator
x_negative = ddgm.generate_x(batchsize_negative)
# train energy model
energy_positive = ddgm.compute_energy_sum(x_positive)
energy_negative = ddgm.compute_energy_sum(x_negative)
loss = energy_positive - energy_negative
ddgm.backprop_energy_model(loss)
# train generative model
# TODO: KLD must be greater than or equal to 0
x_negative = ddgm.generate_x(batchsize_negative)
kld = ddgm.compute_kld_between_generator_and_energy_model(
x_negative)
ddgm.backprop_generative_model(kld)
sum_energy_positive += float(energy_positive.data)
sum_energy_negative += float(energy_negative.data)
sum_loss += float(loss.data)
sum_kld += float(kld.data)
progress.show(t, n_trains_per_epoch, {})
progress.show(
n_trains_per_epoch, n_trains_per_epoch, {
"x+": int(sum_energy_positive / n_trains_per_epoch),
"x-": int(sum_energy_negative / n_trains_per_epoch),
"loss": sum_loss / n_trains_per_epoch,
"kld": sum_kld / n_trains_per_epoch
})
ddgm.save(args.model_dir)
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(
epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
max_epoch = 1000
num_updates_per_epoch = 500
batchsize_true = 128
batchsize_fake = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# init weightnorm layers
if discriminator_config.use_weightnorm:
print "initializing weight normalization layers of the discriminator ..."
x_true = sample_from_data(images, batchsize_true)
gan.discriminate(x_true)
if generator_config.use_weightnorm:
print "initializing weight normalization layers of the generator ..."
gan.generate_x(batchsize_fake)
# training
progress = Progress()
for epoch in xrange(1, max_epoch + 1):
progress.start_epoch(epoch, max_epoch)
sum_loss_unsupervised = 0
sum_loss_adversarial = 0
sum_dx_unlabeled = 0
sum_dx_generated = 0
for t in xrange(num_updates_per_epoch):
# sample data
x_true = sample_from_data(images, batchsize_true)
x_fake = gan.generate_x(batchsize_fake)
x_fake.unchain_backward()
# unsupervised loss
# D(x) = Z(x) / {Z(x) + 1}, where Z(x) = \sum_{k=1}^K exp(l_k(x))
# softplus(x) := log(1 + exp(x))
# logD(x) = logZ(x) - log(Z(x) + 1)
# = logZ(x) - log(exp(log(Z(x))) + 1)
# = logZ(x) - softplus(logZ(x))
# 1 - D(x) = 1 / {Z(x) + 1}
# log{1 - D(x)} = log1 - log(Z(x) + 1)
# = -log(exp(log(Z(x))) + 1)
# = -softplus(logZ(x))
log_zx_u, activations_u = gan.discriminate(x_true,
apply_softmax=False)
log_dx_u = log_zx_u - F.softplus(log_zx_u)
dx_u = F.sum(F.exp(log_dx_u)) / batchsize_true
loss_unsupervised = -F.sum(
log_dx_u) / batchsize_true # minimize negative logD(x)
py_x_g, _ = gan.discriminate(x_fake, apply_softmax=False)
log_zx_g = F.logsumexp(py_x_g, axis=1)
loss_unsupervised += F.sum(F.softplus(
log_zx_g)) / batchsize_true # minimize negative log{1 - D(x)}
# update discriminator
gan.backprop_discriminator(loss_unsupervised)
sum_loss_unsupervised += float(loss_unsupervised.data)
sum_dx_unlabeled += float(dx_u.data)
# generator loss
x_fake = gan.generate_x(batchsize_fake)
log_zx_g, activations_g = gan.discriminate(x_fake,
apply_softmax=False)
log_dx_g = log_zx_g - F.softplus(log_zx_g)
dx_g = F.sum(F.exp(log_dx_g)) / batchsize_fake
loss_generator = -F.sum(
log_dx_g) / batchsize_true # minimize negative logD(x)
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_u[-1]
features_true.unchain_backward()
if batchsize_true != batchsize_fake:
x_fake = gan.generate_x(batchsize_true)
_, activations_g = gan.discriminate(x_fake,
apply_softmax=False)
features_fake = activations_g[-1]
loss_generator += F.mean_squared_error(features_true,
features_fake)
# update generator
gan.backprop_generator(loss_generator)
sum_loss_adversarial += float(loss_generator.data)
sum_dx_generated += float(dx_g.data)
if t % 10 == 0:
progress.show(t, num_updates_per_epoch, {})
gan.save(args.model_dir)
progress.show(
num_updates_per_epoch, num_updates_per_epoch, {
"loss_u": sum_loss_unsupervised / num_updates_per_epoch,
"loss_g": sum_loss_adversarial / num_updates_per_epoch,
"dx_u": sum_dx_unlabeled / num_updates_per_epoch,
"dx_g": sum_dx_generated / num_updates_per_epoch,
})
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(
epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
config = began.config
# settings
max_epoch = 1000
batchsize = 16
num_updates_per_epoch = int(len(images) / batchsize)
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# training
kt = 0
lambda_k = 0.001
progress = Progress()
for epoch in xrange(1, max_epoch + 1):
progress.start_epoch(epoch, max_epoch)
sum_loss_d = 0
sum_loss_g = 0
sum_M = 0
for t in xrange(num_updates_per_epoch):
# sample data
images_real = sample_from_data(images, batchsize)
images_fake = began.generate_x(batchsize)
loss_real = began.compute_loss(images_real)
loss_fake = began.compute_loss(images_fake)
loss_d = loss_real - kt * loss_fake
loss_g = loss_fake
began.backprop_discriminator(loss_d)
began.backprop_generator(loss_g)
loss_d = float(loss_d.data)
loss_g = float(loss_g.data)
loss_real = float(loss_real.data)
loss_fake = float(loss_fake.data)
sum_loss_d += loss_d
sum_loss_g += loss_g
# update control parameters
kt += lambda_k * (config.gamma * loss_real - loss_fake)
kt = max(0, min(1, kt))
M = loss_real + abs(config.gamma * loss_real - loss_fake)
sum_M += M
if t % 10 == 0:
progress.show(t, num_updates_per_epoch, {})
began.save(args.model_dir)
progress.show(
num_updates_per_epoch, num_updates_per_epoch, {
"loss_d": sum_loss_d / num_updates_per_epoch,
"loss_g": sum_loss_g / num_updates_per_epoch,
"k": kt,
"M": sum_M / num_updates_per_epoch,
})
if epoch % plot_interval == 0 or epoch == 1:
plot_generator_outputs(
filename="generator_epoch_{}_time_{}_min".format(
epoch, progress.get_total_time()))
plot_autoencoder_outputs(
images,
filename="autoencoder_epoch_{}_time_{}_min".format(
epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# labels
a = discriminator_config.a
b = discriminator_config.b
c = discriminator_config.c
# settings
max_epoch = 1000
num_updates_per_epoch = 500
batchsize_true = 128
batchsize_fake = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# init weightnorm layers
if discriminator_config.use_weightnorm:
print "initializing weight normalization layers of the discriminator ..."
images_true = sample_from_data(images, batchsize_true)
gan.discriminate(images_true)
if generator_config.use_weightnorm:
print "initializing weight normalization layers of the generator ..."
gan.generate_x(batchsize_fake)
# training
progress = Progress()
for epoch in xrange(1, max_epoch + 1):
progress.start_epoch(epoch, max_epoch)
sum_loss_d = 0
sum_loss_g = 0
for t in xrange(num_updates_per_epoch):
# sample data
images_true = sample_from_data(images, batchsize_true)
images_fake = gan.generate_x(batchsize_true)
images_fake.unchain_backward()
d_true = gan.discriminate(images_true, return_activations=False)
d_fake = gan.discriminate(images_fake, return_activations=False)
loss_d = 0.5 * (F.sum((d_true - b)**2) + F.sum(
(d_fake - a)**2)) / batchsize_true
sum_loss_d += float(loss_d.data)
# update discriminator
gan.backprop_discriminator(loss_d)
# generator loss
images_fake = gan.generate_x(batchsize_fake)
d_fake = gan.discriminate(images_fake, return_activations=False)
loss_g = 0.5 * (F.sum((d_fake - c)**2)) / batchsize_fake
sum_loss_g += float(loss_g.data)
# update generator
gan.backprop_generator(loss_g)
if t % 10 == 0:
progress.show(t, num_updates_per_epoch, {})
gan.save(args.model_dir)
progress.show(
num_updates_per_epoch, num_updates_per_epoch, {
"loss_d": sum_loss_d / num_updates_per_epoch,
"loss_g": sum_loss_g / num_updates_per_epoch,
})
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(
epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
max_epoch = 1000
num_updates_per_epoch = 500
batchsize_true = 128
batchsize_fake = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# init weightnorm layers
if discriminator_config.use_weightnorm:
print "initializing weight normalization layers of the discriminator ..."
x_true = sample_from_data(images, batchsize_true)
gan.discriminate(x_true)
if generator_config.use_weightnorm:
print "initializing weight normalization layers of the generator ..."
gan.generate_x(batchsize_fake)
# training
progress = Progress()
for epoch in xrange(1, max_epoch + 1):
progress.start_epoch(epoch, max_epoch)
sum_loss_critic = 0
sum_loss_generator = 0
learning_rate = get_learning_rate_for_epoch(epoch)
gan.update_learning_rate(learning_rate)
for t in xrange(num_updates_per_epoch):
for k in xrange(discriminator_config.num_critic):
# clamp parameters to a cube
gan.clip_discriminator_weights()
# gan.scale_discriminator_weights()
# sample data
x_true = sample_from_data(images, batchsize_true)
x_fake = gan.generate_x(batchsize_true)
x_fake.unchain_backward()
fw_u, activations_u = gan.discriminate(x_true)
fw_g, _ = gan.discriminate(x_fake)
loss_critic = -F.sum(fw_u - fw_g) / batchsize_true
sum_loss_critic += float(loss_critic.data) / discriminator_config.num_critic
# update discriminator
gan.backprop_discriminator(loss_critic)
# generator loss
x_fake = gan.generate_x(batchsize_fake)
fw_g, activations_g = gan.discriminate(x_fake)
loss_generator = -F.sum(fw_g) / batchsize_fake
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_u[-1]
features_true.unchain_backward()
if batchsize_true != batchsize_fake:
x_fake = gan.generate_x(batchsize_true)
_, activations_g = gan.discriminate(x_fake, apply_softmax=False)
features_fake = activations_g[-1]
loss_generator += F.mean_squared_error(features_true, features_fake)
# update generator
gan.backprop_generator(loss_generator)
sum_loss_generator += float(loss_generator.data)
if t % 10 == 0:
progress.show(t, num_updates_per_epoch, {})
gan.save(args.model_dir)
progress.show(num_updates_per_epoch, num_updates_per_epoch, {
"wasserstein": -sum_loss_critic / num_updates_per_epoch,
"loss_g": sum_loss_generator / num_updates_per_epoch,
"lr": learning_rate
})
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
# config
config = chainer.config
# settings
max_epoch = 1000
num_updates_per_epoch = 500
batchsize_true = 128
batchsize_fake = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# training
progress = Progress()
for epoch in xrange(1, max_epoch + 1):
with chainer.using_config("train", True):
progress.start_epoch(epoch, max_epoch)
sum_loss_critic = 0
sum_loss_generator = 0
learning_rate = get_learning_rate_for_epoch(epoch)
gan.update_learning_rate(learning_rate)
for t in xrange(num_updates_per_epoch):
for k in xrange(config.discriminator.num_critic):
# clamp parameters to a cube
gan.clip_discriminator_weights()
# sample data
x_true = sample_from_data(images, batchsize_true)
x_fake = gan.generate_x(batchsize_true)
x_fake.unchain_backward()
fw_u, activations_u = gan.discriminate(x_true)
fw_g, _ = gan.discriminate(x_fake)
loss_critic = -F.sum(fw_u - fw_g) / batchsize_true
sum_loss_critic += float(
loss_critic.data) / config.discriminator.num_critic
# update discriminator
gan.backprop_discriminator(loss_critic)
# generator loss
x_fake = gan.generate_x(batchsize_fake)
fw_g, activations_g = gan.discriminate(x_fake)
loss_generator = -F.sum(fw_g) / batchsize_fake
# update generator
gan.backprop_generator(loss_generator)
sum_loss_generator += float(loss_generator.data)
if t % 10 == 0:
progress.show(t, num_updates_per_epoch, {})
gan.save(args.model_dir)
progress.show(
num_updates_per_epoch, num_updates_per_epoch, {
"wasserstein": -sum_loss_critic / num_updates_per_epoch,
"loss_g": sum_loss_generator / num_updates_per_epoch,
"lr": learning_rate
})
with chainer.using_config("train", False):
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(
epoch, progress.get_total_time()))
def main():
images = load_rgb_images(args.image_dir)
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
max_epoch = 1000
n_trains_per_epoch = 500
batchsize_true = 128
batchsize_fake = 128
plot_interval = 5
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# init weightnorm layers
if discriminator_config.use_weightnorm:
print "initializing weight normalization layers of the discriminator ..."
x_true = sample_from_data(images, batchsize_true)
gan.discriminate(x_true)
if generator_config.use_weightnorm:
print "initializing weight normalization layers of the generator ..."
gan.generate_x(batchsize_fake)
# classification
# 0 -> true sample
# 1 -> generated sample
class_true = gan.to_variable(np.zeros(batchsize_true, dtype=np.int32))
class_fake = gan.to_variable(np.ones(batchsize_fake, dtype=np.int32))
# training
progress = Progress()
for epoch in xrange(1, max_epoch):
progress.start_epoch(epoch, max_epoch)
sum_loss_discriminator = 0
sum_loss_generator = 0
sum_loss_vat = 0
for t in xrange(n_trains_per_epoch):
# sample data
x_true = sample_from_data(images, batchsize_true)
x_fake = gan.generate_x(batchsize_fake).data # unchain
# train discriminator
discrimination_true, activations_true = gan.discriminate(
x_true, apply_softmax=False)
discrimination_fake, _ = gan.discriminate(x_fake,
apply_softmax=False)
loss_discriminator = F.softmax_cross_entropy(
discrimination_true, class_true) + F.softmax_cross_entropy(
discrimination_fake, class_fake)
gan.backprop_discriminator(loss_discriminator)
# virtual adversarial training
loss_vat = 0
if discriminator_config.use_virtual_adversarial_training:
z = gan.sample_z(batchsize_fake)
loss_vat = -F.sum(gan.compute_lds(z)) / batchsize_fake
gan.backprop_discriminator(loss_vat)
sum_loss_vat += float(loss_vat.data)
# train generator
x_fake = gan.generate_x(batchsize_fake)
discrimination_fake, activations_fake = gan.discriminate(
x_fake, apply_softmax=False)
loss_generator = F.softmax_cross_entropy(discrimination_fake,
class_true)
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_true[-1]
features_fake = activations_fake[-1]
loss_generator += F.mean_squared_error(features_true,
features_fake)
gan.backprop_generator(loss_generator)
sum_loss_discriminator += float(loss_discriminator.data)
sum_loss_generator += float(loss_generator.data)
if t % 10 == 0:
progress.show(t, n_trains_per_epoch, {})
progress.show(
n_trains_per_epoch, n_trains_per_epoch, {
"loss_d": sum_loss_discriminator / n_trains_per_epoch,
"loss_g": sum_loss_generator / n_trains_per_epoch,
"loss_vat": sum_loss_vat / n_trains_per_epoch,
})
gan.save(args.model_dir)
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(
epoch, progress.get_total_time()))