def train(model,
output_dir,
train_feed,
test_feed,
lr_start=0.01,
lr_stop=0.00001,
lr_gamma=0.75,
n_epochs=150,
gan_margin=0.35):
n_hidden = model.latent_encoder.n_out
# For plotting
original_x = np.array(test_feed.batches().next()[0])
samples_z = np.random.normal(size=(len(original_x), n_hidden))
samples_z = (samples_z).astype(dp.float_)
recon_video = Video(os.path.join(output_dir, 'convergence_recon.mp4'))
sample_video = Video(os.path.join(output_dir, 'convergence_samples.mp4'))
original_x_ = original_x
original_x_ = img_inverse_transform(original_x)
sp.misc.imsave(os.path.join(output_dir, 'examples.png'),
dp.misc.img_tile(original_x_))
# Train network
learn_rule = dp.RMSProp()
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
trainer = aegan.GradientDescent(model,
train_feed,
learn_rule,
margin=gan_margin)
try:
for e in range(n_epochs):
model.phase = 'train'
model.setup(*train_feed.shapes)
learn_rule.learn_rate = annealer.value(e) / train_feed.batch_size
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(samples_x)
recon_video.append(dp.misc.img_tile(recon_x))
sample_video.append(dp.misc.img_tile(samples_x))
except KeyboardInterrupt:
pass
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, output_dir, img_inverse_transform)
output.reconstructions(model, original_x, output_dir,
img_inverse_transform)
original_z = model.encode(original_x)
output.walk(model, original_z, output_dir, img_inverse_transform)
return model
def train(
model,
output_dir,
train_feed,
test_feed,
lr_start=0.01,
lr_stop=0.00001,
lr_gamma=0.75,
n_epochs=150,
gan_margin=0.35,
):
n_hidden = model.latent_encoder.n_out
# For plotting
original_x = np.array(test_feed.batches().next()[0])
samples_z = np.random.normal(size=(len(original_x), n_hidden))
samples_z = (samples_z).astype(dp.float_)
recon_video = Video(os.path.join(output_dir, "convergence_recon.mp4"))
sample_video = Video(os.path.join(output_dir, "convergence_samples.mp4"))
original_x_ = original_x
original_x_ = img_inverse_transform(original_x)
sp.misc.imsave(os.path.join(output_dir, "examples.png"), dp.misc.img_tile(original_x_))
# Train network
learn_rule = dp.RMSProp()
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
trainer = aegan.GradientDescent(model, train_feed, learn_rule, margin=gan_margin)
try:
for e in range(n_epochs):
model.phase = "train"
model.setup(*train_feed.shapes)
learn_rule.learn_rate = annealer.value(e) / train_feed.batch_size
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(samples_x)
recon_video.append(dp.misc.img_tile(recon_x))
sample_video.append(dp.misc.img_tile(samples_x))
except KeyboardInterrupt:
pass
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, output_dir, img_inverse_transform)
output.reconstructions(model, original_x, output_dir, img_inverse_transform)
original_z = model.encode(original_x)
output.walk(model, original_z, output_dir, img_inverse_transform)
return model
def run():
experiment_name = 'celeba'
img_size = 64
epoch_size = 1
batch_size = 2000
n_hidden = 128
_, experiment_name = aegan.build_model(
experiment_name,
img_size,
n_hidden=n_hidden,
recon_depth=9,
recon_vs_gan_weight=1e-6,
real_vs_gen_weight=0.5,
discriminate_ae_recon=False,
discriminate_sample_z=True,
)
print('experiment_name: %s' % experiment_name)
output_dir = os.path.join('out', experiment_name)
model_path = os.path.join(output_dir, 'arch.pickle')
print('Loading model from disk')
print(model_path)
with open(model_path, 'rb') as f:
model = pickle.load(f)
print('Getting data feed')
model.phase = 'test'
train_feed, test_feed = dataset.celeba.feeds(img_size,
batch_size=batch_size,
epoch_size=epoch_size,
split='test',
n_augment=0)
save_dir = os.path.join(output_dir, 'User-Testing')
if not os.path.expanduser(save_dir):
os.mkdir(save_dir)
original_x = np.array(test_feed.batches().next()[0])
samples_z = np.random.normal(size=(len(original_x), n_hidden))
samples_z = (samples_z).astype(dp.float_)
print('Saving samples')
output.samples(model, samples_z, save_dir, img_inverse_transform)
print('Saving reconstructions')
output.reconstructions(model, original_x, save_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.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():
n_hidden = 128
real_vs_gen_weight = 0.75
gan_margin = 0.3
lr_start = 0.04
lr_stop = 0.0001
lr_gamma = 0.75
n_epochs = 150
epoch_size = 250
batch_size = 64
experiment_name = 'mnist_gan'
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')
_, decoder, discriminator = architectures.mnist()
else:
print('Starting from %s' % start_arch_path)
with open(start_arch_path, 'rb') as f:
decoder, discriminator = pickle.load(f)
model = gan.GAN(
n_hidden=n_hidden,
generator=decoder,
discriminator=discriminator,
real_vs_gen_weight=real_vs_gen_weight,
)
# 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 = gan.GradientDescent(model, train_input, learn_rule,
margin=gan_margin)
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
try:
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
trainer.train_epoch()
model.phase = 'test'
samples_x = model.decode(samples_z)
samples_x = mnist_inverse_transform(model.decode(samples_z))
sample_video.append(dp.misc.img_tile(samples_x))
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():
n_hidden = 128
real_vs_gen_weight = 0.75
gan_margin = 0.3
lr_start = 0.04
lr_stop = 0.0001
lr_gamma = 0.75
n_epochs = 150
epoch_size = 250
batch_size = 64
experiment_name = 'mnist_gan'
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')
_, decoder, discriminator = architectures.mnist()
else:
print('Starting from %s' % start_arch_path)
with open(start_arch_path, 'rb') as f:
decoder, discriminator = pickle.load(f)
model = gan.GAN(
n_hidden=n_hidden,
generator=decoder,
discriminator=discriminator,
real_vs_gen_weight=real_vs_gen_weight,
)
# 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 = gan.GradientDescent(model,
train_feed,
learn_rule,
margin=gan_margin)
annealer = dp.GammaAnnealer(lr_start, lr_stop, n_epochs, gamma=lr_gamma)
try:
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
trainer.train_epoch()
model.phase = 'test'
samples_x = model.decode(samples_z)
samples_x = mnist_inverse_transform(model.decode(samples_z))
sample_video.append(dp.misc.img_tile(samples_x))
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)
