def run_method_1():
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
num_col = 10
num_generation = 20
batchsize = 2 * num_generation
base_z = gan.to_variable(gan.sample_z(batchsize))
# optimize z
class_true = gan.to_variable(np.zeros(batchsize, dtype=np.int32))
for n in xrange(5):
x_fake = gan.generate_x_from_z(base_z, test=True, as_numpy=False)
discrimination_fake, _ = gan.discriminate(x_fake,
apply_softmax=False,
test=True)
cross_entropy = F.softmax_cross_entropy(discrimination_fake,
class_true)
gan.backprop_generator(cross_entropy)
base_z = gan.to_variable(base_z.data + base_z.grad * 0.01)
base_z = gan.to_numpy(base_z)
sum_z = np.sum(base_z)
if sum_z != sum_z:
raise Exception("NaN")
mix_z = np.zeros((num_col * num_generation, generator_config.ndim_input),
dtype=np.float32)
for g in xrange(num_generation):
for i in xrange(num_col):
mix_z[g * num_col +
i] = base_z[2 * g] * (i / float(num_col)) + base_z[
2 * g + 1] * (1 - i / float(num_col))
x_negative = gan.generate_x_from_z(mix_z, test=True, as_numpy=True)
x_negative = (x_negative + 1.0) / 2.0
visualizer.tile_rgb_images(x_negative.transpose(0, 2, 3, 1),
dir=args.plot_dir,
filename="analogy_1",
row=num_generation,
col=num_col)
def main():
# load MNIST images
images, labels = dataset.load_train_images()
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
max_epoch = 1000
num_updates_per_epoch = 500
plot_interval = 5
batchsize_true = 100
batchsize_fake = batchsize_true
# 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):
progress.start_epoch(epoch, max_epoch)
sum_loss_critic = 0
sum_loss_generator = 0
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.decay_discriminator_weights()
# sample true data from data distribution
images_true = dataset.sample_data(images, batchsize_true, binarize=False)
# sample fake data from generator
images_fake = gan.generate_x(batchsize_fake)
images_fake.unchain_backward()
fw_true, activations_true = gan.discriminate(images_true)
fw_fake, _ = gan.discriminate(images_fake)
loss_critic = -F.sum(fw_true - fw_fake) / batchsize_true
sum_loss_critic += float(loss_critic.data) / discriminator_config.num_critic
# update discriminator
gan.backprop_discriminator(loss_critic)
# generator loss
images_fake = gan.generate_x(batchsize_fake)
fw_fake, activations_fake = gan.discriminate(images_fake)
loss_generator = -F.sum(fw_fake) / batchsize_fake
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_true[-1]
features_true.unchain_backward()
if batchsize_true != batchsize_fake:
images_fake = gan.generate_x(batchsize_true)
_, activations_fake = gan.discriminate(images_fake, apply_softmax=False)
features_fake = activations_fake[-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,
})
if epoch % plot_interval == 0 or epoch == 1:
plot(filename="epoch_{}_time_{}min".format(epoch, progress.get_total_time()))
def main():
# load MNIST images
images, labels = dataset.load_train_images()
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
# _l -> labeled
# _u -> unlabeled
# _g -> generated
max_epoch = 1000
num_trains_per_epoch = 500
plot_interval = 5
batchsize_l = 100
batchsize_u = 100
batchsize_g = batchsize_u
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# save validation accuracy per epoch
csv_results = []
# create semi-supervised split
num_validation_data = 10000
num_labeled_data = args.num_labeled
if batchsize_l > num_labeled_data:
batchsize_l = num_labeled_data
training_images_l, training_labels_l, training_images_u, validation_images, validation_labels = dataset.create_semisupervised(
images,
labels,
num_validation_data,
num_labeled_data,
discriminator_config.ndim_output,
seed=args.seed)
print training_labels_l
# training
progress = Progress()
for epoch in xrange(1, max_epoch):
progress.start_epoch(epoch, max_epoch)
sum_loss_supervised = 0
sum_loss_unsupervised = 0
sum_loss_adversarial = 0
sum_dx_labeled = 0
sum_dx_unlabeled = 0
sum_dx_generated = 0
gan.update_learning_rate(get_learning_rate_for_epoch(epoch))
for t in xrange(num_trains_per_epoch):
# sample from data distribution
images_l, label_onehot_l, label_ids_l = dataset.sample_labeled_data(
training_images_l,
training_labels_l,
batchsize_l,
discriminator_config.ndim_input,
discriminator_config.ndim_output,
binarize=False)
images_u = dataset.sample_unlabeled_data(
training_images_u,
batchsize_u,
discriminator_config.ndim_input,
binarize=False)
images_g = gan.generate_x(batchsize_g)
images_g.unchain_backward()
# supervised loss
py_x_l, activations_l = gan.discriminate(images_l,
apply_softmax=False)
loss_supervised = F.softmax_cross_entropy(
py_x_l, gan.to_variable(label_ids_l))
log_zx_l = F.logsumexp(py_x_l, axis=1)
log_dx_l = log_zx_l - F.softplus(log_zx_l)
dx_l = F.sum(F.exp(log_dx_l)) / batchsize_l
# 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))
py_x_u, _ = gan.discriminate(images_u, apply_softmax=False)
log_zx_u = F.logsumexp(py_x_u, axis=1)
log_dx_u = log_zx_u - F.softplus(log_zx_u)
dx_u = F.sum(F.exp(log_dx_u)) / batchsize_u
loss_unsupervised = -F.sum(
log_dx_u) / batchsize_u # minimize negative logD(x)
py_x_g, _ = gan.discriminate(images_g, apply_softmax=False)
log_zx_g = F.logsumexp(py_x_g, axis=1)
loss_unsupervised += F.sum(F.softplus(
log_zx_g)) / batchsize_u # minimize negative log{1 - D(x)}
# update discriminator
gan.backprop_discriminator(loss_supervised + loss_unsupervised)
# adversarial loss
images_g = gan.generate_x(batchsize_g)
py_x_g, activations_g = gan.discriminate(images_g,
apply_softmax=False)
log_zx_g = F.logsumexp(py_x_g, axis=1)
log_dx_g = log_zx_g - F.softplus(log_zx_g)
dx_g = F.sum(F.exp(log_dx_g)) / batchsize_g
loss_adversarial = -F.sum(
log_dx_g) / batchsize_u # minimize negative logD(x)
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_l[-1]
features_true.unchain_backward()
if batchsize_l != batchsize_g:
images_g = gan.generate_x(batchsize_l)
_, activations_g = gan.discriminate(images_g,
apply_softmax=False)
features_fake = activations_g[-1]
loss_adversarial += F.mean_squared_error(
features_true, features_fake)
# update generator
gan.backprop_generator(loss_adversarial)
sum_loss_supervised += float(loss_supervised.data)
sum_loss_unsupervised += float(loss_unsupervised.data)
sum_loss_adversarial += float(loss_adversarial.data)
sum_dx_labeled += float(dx_l.data)
sum_dx_unlabeled += float(dx_u.data)
sum_dx_generated += float(dx_g.data)
if t % 10 == 0:
progress.show(t, num_trains_per_epoch, {})
gan.save(args.model_dir)
# validation
images_l, _, label_ids_l = dataset.sample_labeled_data(
validation_images,
validation_labels,
num_validation_data,
discriminator_config.ndim_input,
discriminator_config.ndim_output,
binarize=False)
images_l_segments = np.split(images_l, num_validation_data // 500)
label_ids_l_segments = np.split(label_ids_l,
num_validation_data // 500)
sum_accuracy = 0
for images_l, label_ids_l in zip(images_l_segments,
label_ids_l_segments):
y_distribution, _ = gan.discriminate(images_l,
apply_softmax=True,
test=True)
accuracy = F.accuracy(y_distribution, gan.to_variable(label_ids_l))
sum_accuracy += float(accuracy.data)
validation_accuracy = sum_accuracy / len(images_l_segments)
progress.show(
num_trains_per_epoch, num_trains_per_epoch, {
"loss_l": sum_loss_supervised / num_trains_per_epoch,
"loss_u": sum_loss_unsupervised / num_trains_per_epoch,
"loss_g": sum_loss_adversarial / num_trains_per_epoch,
"dx_l": sum_dx_labeled / num_trains_per_epoch,
"dx_u": sum_dx_unlabeled / num_trains_per_epoch,
"dx_g": sum_dx_generated / num_trains_per_epoch,
"accuracy": validation_accuracy,
})
# write accuracy to csv
csv_results.append(
[epoch, validation_accuracy,
progress.get_total_time()])
data = pd.DataFrame(csv_results)
data.columns = ["epoch", "accuracy", "min"]
data.to_csv("{}/result.csv".format(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():
# 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 = 200
num_updates_per_epoch = 500
plot_interval = 5
batchsize_true = 100
batchsize_fake = batchsize_true
scale = 2.0
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# training
progress = Progress()
plot_samples(0, 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 from data distribution
samples_true = sampler.gaussian_mixture_circle(
batchsize_true,
generator_config.num_mixture,
scale=scale,
std=0.2)
# sample from generator
samples_fale = gan.generate_x(batchsize_true, from_gaussian=True)
samples_fale.unchain_backward()
d_true = gan.discriminate(samples_true / scale,
return_activations=False)
d_fake = gan.discriminate(samples_fale / scale,
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
samples_fale = gan.generate_x(batchsize_fake, from_gaussian=True)
d_fake = gan.discriminate(samples_fale / scale,
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_samples(epoch, progress)
def main():
# config
discriminator_config = gan.config_discriminator
generator_config = gan.config_generator
# settings
max_epoch = 200
num_updates_per_epoch = 500
plot_interval = 5
batchsize_true = 100
batchsize_fake = batchsize_true
scale = 2.0
# seed
np.random.seed(args.seed)
if args.gpu_device != -1:
cuda.cupy.random.seed(args.seed)
# training
progress = Progress()
plot_samples(0, progress)
for epoch in xrange(1, max_epoch + 1):
progress.start_epoch(epoch, max_epoch)
sum_loss_critic = 0
sum_loss_generator = 0
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.decay_discriminator_weights()
# sample from data distribution
samples_true = sampler.gaussian_mixture_circle(
batchsize_true,
generator_config.num_mixture,
scale=scale,
std=0.2)
# sample from generator
samples_fale = gan.generate_x(batchsize_true,
from_gaussian=True)
samples_fale.unchain_backward()
fw_true, activations_true = gan.discriminate(samples_true /
scale)
fw_fake, _ = gan.discriminate(samples_fale / scale)
loss_critic = -F.sum(fw_true - fw_fake) / batchsize_true
sum_loss_critic += float(
loss_critic.data) / discriminator_config.num_critic
# update discriminator
gan.backprop_discriminator(loss_critic)
# generator loss
samples_fale = gan.generate_x(batchsize_fake, from_gaussian=True)
fw_fake, activations_fake = gan.discriminate(samples_fale / scale)
loss_generator = -F.sum(fw_fake) / batchsize_fake
# feature matching
if discriminator_config.use_feature_matching:
features_true = activations_true[-1]
features_true.unchain_backward()
if batchsize_true != batchsize_fake:
samples_fale = gan.generate_x(batchsize_true,
from_gaussian=True)
_, activations_fake = gan.discriminate(samples_fale /
scale)
features_fake = activations_fake[-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,
})
if epoch % plot_interval == 0 or epoch == 1:
plot_samples(epoch, progress)
def main():
# load MNIST images
images, labels = dataset.load_train_images()
# 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
plot_interval = 5
batchsize_true = 100
batchsize_fake = batchsize_true
# 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):
progress.start_epoch(epoch, max_epoch)
sum_loss_d = 0
sum_loss_g = 0
for t in xrange(num_updates_per_epoch):
# sample true data from data distribution
images_true = dataset.sample_data(images,
batchsize_true,
binarize=False)
# sample fake data from generator
images_fake = gan.generate_x(batchsize_fake)
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
# 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()))