def build_model(
experiment_name,
img_size,
n_hidden=128,
recon_depth=9,
recon_vs_gan_weight=5e-5,
real_vs_gen_weight=0.5,
discriminate_sample_z=True,
discriminate_ae_recon=True,
wgain=1.0,
wdecay=1e-5,
bn_noise_std=0.0,
):
if n_hidden != 128:
experiment_name += "_nhidden%i" % n_hidden
experiment_name += "_reconganweight%.1e" % recon_vs_gan_weight
if recon_depth > 0:
experiment_name += "_recondepth%i" % recon_depth
if not np.isclose(real_vs_gen_weight, 0.5):
experiment_name += "_realgenweight%.2f" % real_vs_gen_weight
if not discriminate_sample_z:
experiment_name += "_nodissamplez"
if not discriminate_ae_recon:
experiment_name += "_nodisaerecon"
if not np.isclose(wgain, 1.0):
experiment_name += "_wgain%.1e" % wgain
if not np.isclose(wdecay, 1e-5):
experiment_name += "_wdecay%.1e" % wdecay
if not np.isclose(bn_noise_std, 0.0):
experiment_name += "_bnnoise%.2f" % bn_noise_std
# Setup network
if img_size == 32:
encoder, decoder, discriminator = architectures.img32x32(wgain=wgain, wdecay=wdecay, bn_noise_std=bn_noise_std)
elif img_size == 64:
encoder, decoder, discriminator = architectures.img64x64(wgain=wgain, wdecay=wdecay, bn_noise_std=bn_noise_std)
else:
raise ValueError("no architecture for img_size %i" % img_size)
latent_encoder = architectures.vae_latent_encoder(n_hidden)
model = aegan.AEGAN(
encoder=encoder,
latent_encoder=latent_encoder,
decoder=decoder,
discriminator=discriminator,
recon_depth=recon_depth,
discriminate_sample_z=discriminate_sample_z,
discriminate_ae_recon=discriminate_ae_recon,
recon_vs_gan_weight=recon_vs_gan_weight,
real_vs_gen_weight=real_vs_gen_weight,
)
return model, experiment_name
def build_model(experiment_name,
img_size,
n_hidden=128,
recon_depth=9,
recon_vs_gan_weight=5e-5,
real_vs_gen_weight=0.5,
discriminate_sample_z=True,
discriminate_ae_recon=True,
wgain=1.0,
wdecay=1e-5,
bn_noise_std=0.0):
if n_hidden != 128:
experiment_name += '_nhidden%i' % n_hidden
experiment_name += '_reconganweight%.1e' % recon_vs_gan_weight
if recon_depth > 0:
experiment_name += '_recondepth%i' % recon_depth
if not np.isclose(real_vs_gen_weight, 0.5):
experiment_name += '_realgenweight%.2f' % real_vs_gen_weight
if not discriminate_sample_z:
experiment_name += '_nodissamplez'
if not discriminate_ae_recon:
experiment_name += '_nodisaerecon'
if not np.isclose(wgain, 1.0):
experiment_name += '_wgain%.1e' % wgain
if not np.isclose(wdecay, 1e-5):
experiment_name += '_wdecay%.1e' % wdecay
if not np.isclose(bn_noise_std, 0.0):
experiment_name += '_bnnoise%.2f' % bn_noise_std
# Setup network
if img_size == 32:
encoder, decoder, discriminator = architectures.img32x32(
wgain=wgain, wdecay=wdecay, bn_noise_std=bn_noise_std)
elif img_size == 64:
encoder, decoder, discriminator = architectures.img64x64(
wgain=wgain, wdecay=wdecay, bn_noise_std=bn_noise_std)
else:
raise ValueError('no architecture for img_size %i' % img_size)
latent_encoder = architectures.vae_latent_encoder(n_hidden)
model = aegan.AEGAN(
encoder=encoder,
latent_encoder=latent_encoder,
decoder=decoder,
discriminator=discriminator,
recon_depth=recon_depth,
discriminate_sample_z=discriminate_sample_z,
discriminate_ae_recon=discriminate_ae_recon,
recon_vs_gan_weight=recon_vs_gan_weight,
real_vs_gen_weight=real_vs_gen_weight,
)
return model, experiment_name
def run():
n_hidden = 64
ae_kind = 'variational'
lr_start = 0.01
lr_stop = 0.0001
lr_gamma = 0.75
n_epochs = 150
epoch_size = 250
batch_size = 64
experiment_name = 'mnist_ae'
experiment_name += '_nhidden%i' % n_hidden
out_dir = os.path.join('out', experiment_name)
arch_path = os.path.join(out_dir, 'arch.pickle')
start_arch_path = arch_path
start_arch_path = None
print('experiment_name', experiment_name)
print('start_arch_path', start_arch_path)
print('arch_path', arch_path)
# Setup network
if start_arch_path is None:
print('Creating new model')
encoder, decoder, _ = architectures.mnist()
if ae_kind == 'variational':
latent_encoder = architectures.vae_latent_encoder(n_hidden)
elif ae_kind == 'adversarial':
latent_encoder = architectures.aae_latent_encoder(n_hidden)
else:
print('Starting from %s' % start_arch_path)
with open(start_arch_path, 'rb') as f:
decoder, discriminator = pickle.load(f)
model = ae.Autoencoder(
encoder=encoder,
latent_encoder=latent_encoder,
decoder=decoder,
)
model.recon_error = ae.GaussianNegLogLikelihood()
# Fetch dataset
dataset = dp.dataset.MNIST()
x_train, y_train, x_test, y_test = dataset.arrays()
x_train = mnist_transform(x_train)
x_test = mnist_transform(x_test)
# Prepare network inputs
train_input = dp.Input(x_train, batch_size, epoch_size)
test_input = dp.Input(x_test, batch_size)
# Plotting
n_examples = 64
batch = test_input.batches().next()
original_x = batch['x']
original_x = np.array(original_x)[:n_examples]
samples_z = np.random.normal(size=(n_examples, n_hidden))
samples_z = (samples_z).astype(dp.float_)
# Train network
learn_rule = dp.RMSProp()
trainer = dp.GradientDescent(model, train_input, learn_rule)
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
try:
recon_video = Video(os.path.join(out_dir, 'convergence_recon.mp4'))
sample_video = Video(os.path.join(out_dir, 'convergence_samples.mp4'))
sp.misc.imsave(os.path.join(out_dir, 'examples.png'),
dp.misc.img_tile(mnist_inverse_transform(original_x)))
for e in range(n_epochs):
model.phase = 'train'
model.setup(**train_input.shapes)
learn_rule.learn_rate = annealer.value(e) / batch_size
loss = trainer.train_epoch()
model.phase = 'test'
original_z = model.encode(original_x)
recon_x = model.decode(original_z)
samples_x = model.decode(samples_z)
recon_x = mnist_inverse_transform(recon_x)
samples_x = mnist_inverse_transform(model.decode(samples_z))
recon_video.append(dp.misc.img_tile(recon_x))
sample_video.append(dp.misc.img_tile(samples_x))
likelihood = model.likelihood(test_input)
print('epoch %i Train loss:%.4f Test likelihood:%.4f' %
(e, np.mean(loss), np.mean(likelihood)))
except KeyboardInterrupt:
pass
print('Saving model to disk')
with open(arch_path, 'wb') as f:
pickle.dump((decoder, discriminator), f)
model.phase = 'test'
n_examples = 100
samples_z = np.random.normal(size=(n_examples, n_hidden)).astype(dp.float_)
output.samples(model, samples_z, out_dir, mnist_inverse_transform)
output.walk(model, samples_z, out_dir, mnist_inverse_transform)
def run():
experiment_name = 'celeba-ae'
img_size = 64
epoch_size = 250
batch_size = 64
n_hidden = 128
n_augment = int(6e5)
train_feed, test_feed = dataset.celeba.feeds(
img_size,
split='test',
batch_size=batch_size,
epoch_size=epoch_size,
n_augment=n_augment,
)
experiment_name += '_nhidden%i' % n_hidden
out_dir = os.path.join('out', experiment_name)
arch_path = os.path.join(out_dir, 'arch.pickle')
start_arch_path = arch_path
start_arch_path = None
print('experiment_name', experiment_name)
print('start_arch_path', start_arch_path)
print('arch_path', arch_path)
ae_kind = 'variational'
# Setup network
if start_arch_path is None:
print('Creating new model')
encoder, decoder, _ = architectures.img64x64()
if ae_kind == 'variational':
latent_encoder = architectures.vae_latent_encoder(n_hidden)
elif ae_kind == 'adversarial':
latent_encoder = architectures.aae_latent_encoder(n_hidden)
else:
print('Starting from %s' % start_arch_path)
with open(start_arch_path, 'rb') as f:
encoder, latent_encoder, decoder = pickle.load(f)
model = ae.Autoencoder(
encoder=encoder,
latent_encoder=latent_encoder,
decoder=decoder,
)
model.recon_error = ae.NLLNormal()
# Plotting
n_examples = 64
original_x, = test_feed.batches().next()
original_x = np.array(original_x)[:n_examples]
samples_z = np.random.normal(size=(n_examples, n_hidden))
samples_z = (samples_z).astype(dp.float_)
n_epochs = 250
lr_start = 0.025
lr_stop = 0.00001
lr_gamma = 0.75
# Train network
learn_rule = dp.RMSProp()
trainer = dp.GradientDescent(model, train_feed, learn_rule)
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
try:
recon_video = Video(os.path.join(out_dir, 'convergence_recon.mp4'))
sample_video = Video(os.path.join(out_dir, 'convergence_samples.mp4'))
sp.misc.imsave(os.path.join(out_dir, 'examples.png'),
dp.misc.img_tile(img_inverse_transform(original_x)))
for e in range(n_epochs):
model.phase = 'train'
model.setup(*train_feed.shapes)
learn_rule.learn_rate = annealer.value(e) / batch_size
loss = trainer.train_epoch()
model.phase = 'test'
original_z = model.encode(original_x)
recon_x = model.decode(original_z)
samples_x = model.decode(samples_z)
recon_x = img_inverse_transform(recon_x)
samples_x = img_inverse_transform(model.decode(samples_z))
recon_video.append(dp.misc.img_tile(recon_x))
sample_video.append(dp.misc.img_tile(samples_x))
likelihood = model.likelihood(test_feed)
print(
'epoch %i Train loss:%.4f Test likelihood:%.4f Learn Rate:%.4f'
%
(e, np.mean(loss), np.mean(likelihood), learn_rule.learn_rate))
except KeyboardInterrupt:
pass
print('Saving model to disk')
with open(arch_path, 'wb') as f:
pickle.dump((encoder, latent_encoder, decoder), f)
model.phase = 'test'
n_examples = 100
test_feed.reset()
original_x = np.array(test_feed.batches().next()[0])[:n_examples]
samples_z = np.random.normal(size=(n_examples, n_hidden))
output.samples(model, samples_z, out_dir, img_inverse_transform)
output.reconstructions(model, original_x, out_dir, img_inverse_transform)
original_z = model.encode(original_x)
output.walk(model, original_z, out_dir, img_inverse_transform)
def run():
n_hidden = 64
ae_kind = 'variational'
lr_start = 0.01
lr_stop = 0.0001
lr_gamma = 0.75
n_epochs = 150
epoch_size = 250
batch_size = 64
experiment_name = 'mnist_ae'
experiment_name += '_nhidden%i' % n_hidden
out_dir = os.path.join('out', experiment_name)
arch_path = os.path.join(out_dir, 'arch.pickle')
start_arch_path = arch_path
start_arch_path = None
print('experiment_name', experiment_name)
print('start_arch_path', start_arch_path)
print('arch_path', arch_path)
# Setup network
if start_arch_path is None:
print('Creating new model')
encoder, decoder, _ = architectures.mnist()
if ae_kind == 'variational':
latent_encoder = architectures.vae_latent_encoder(n_hidden)
elif ae_kind == 'adversarial':
latent_encoder = architectures.aae_latent_encoder(n_hidden)
else:
print('Starting from %s' % start_arch_path)
with open(start_arch_path, 'rb') as f:
decoder, discriminator = pickle.load(f)
model = ae.Autoencoder(
encoder=encoder,
latent_encoder=latent_encoder,
decoder=decoder,
)
model.recon_error = ae.NLLNormal()
# Fetch dataset
dataset = dp.dataset.MNIST()
x_train, y_train, x_test, y_test = dataset.arrays()
x_train = mnist_transform(x_train)
x_test = mnist_transform(x_test)
# Prepare network feeds
train_feed = dp.Feed(x_train, batch_size, epoch_size)
test_feed = dp.Feed(x_test, batch_size)
# Plotting
n_examples = 64
original_x, = test_feed.batches().next()
original_x = np.array(original_x)[:n_examples]
samples_z = np.random.normal(size=(n_examples, n_hidden))
samples_z = (samples_z).astype(dp.float_)
# Train network
learn_rule = dp.RMSProp()
trainer = dp.GradientDescent(model, train_feed, learn_rule)
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
try:
recon_video = Video(os.path.join(out_dir, 'convergence_recon.mp4'))
sample_video = Video(os.path.join(out_dir, 'convergence_samples.mp4'))
sp.misc.imsave(os.path.join(out_dir, 'examples.png'),
dp.misc.img_tile(mnist_inverse_transform(original_x)))
for e in range(n_epochs):
model.phase = 'train'
model.setup(*train_feed.shapes)
learn_rule.learn_rate = annealer.value(e) / batch_size
loss = trainer.train_epoch()
model.phase = 'test'
original_z = model.encode(original_x)
recon_x = model.decode(original_z)
samples_x = model.decode(samples_z)
recon_x = mnist_inverse_transform(recon_x)
samples_x = mnist_inverse_transform(model.decode(samples_z))
recon_video.append(dp.misc.img_tile(recon_x))
sample_video.append(dp.misc.img_tile(samples_x))
likelihood = model.likelihood(test_feed)
print('epoch %i Train loss:%.4f Test likelihood:%.4f' %
(e, np.mean(loss), np.mean(likelihood)))
except KeyboardInterrupt:
pass
print('Saving model to disk')
with open(arch_path, 'wb') as f:
pickle.dump((decoder, discriminator), f)
model.phase = 'test'
n_examples = 100
samples_z = np.random.normal(size=(n_examples, n_hidden)).astype(dp.float_)
output.samples(model, samples_z, out_dir, mnist_inverse_transform)
output.walk(model, samples_z, out_dir, mnist_inverse_transform)