def run():
mode = 'vaegan'
vae_grad_scale = 0.025
experiment_name = mode + 'scale_%.5f' % vae_grad_scale
filename = 'savestates/mnist_' + experiment_name + '.pickle'
in_filename = filename
in_filename = None
print('experiment_name', experiment_name)
print('in_filename', in_filename)
print('filename', filename)
# Fetch dataset
dataset = dp.dataset.MNIST()
x_train, y_train, x_test, y_test = dataset.arrays(dp_dtypes=True)
n_classes = dataset.n_classes
img_shape = x_train.shape[1:]
# Normalize pixel intensities
scaler = dp.UniformScaler()
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
y_train = one_hot(y_train, n_classes).astype(dp.float_)
y_test = one_hot(y_test, n_classes).astype(dp.float_)
x_train = np.reshape(x_train, (x_train.shape[0], -1))
x_test = np.reshape(x_test, (x_test.shape[0], -1))
# Setup network
if in_filename is None:
print('Creating new model')
expressions = model_expressions(img_shape)
else:
print('Starting from %s' % in_filename)
with open(in_filename, 'rb') as f:
expressions = pickle.load(f)
encoder, sampler, generator, discriminator = expressions
model = cond_vaegan.ConditionalVAEGAN(
encoder=encoder,
sampler=sampler,
generator=generator,
discriminator=discriminator,
mode=mode,
reconstruct_error=expr.nnet.BinaryCrossEntropy(),
vae_grad_scale=vae_grad_scale,
)
# Prepare network inputs
batch_size = 128
train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size,
epoch_size=250)
# Plotting
n_examples = 100
examples = x_test[:n_examples]
examples_y = y_test[:n_examples]
samples_z = np.random.normal(size=(n_examples, model.sampler.n_hidden))
samples_z = samples_z.astype(dp.float_)
samples_y = ((np.arange(n_examples) // 10) % n_classes)
samples_y = one_hot(samples_y, n_classes).astype(dp.float_)
recon_video = Video('plots/mnist_' + experiment_name +
'_reconstruction.mp4')
sample_video = Video('plots/mnist_' + experiment_name + '_samples.mp4')
sp.misc.imsave('plots/mnist_examples.png',
img_tile(to_b01c(examples, img_shape)))
def plot():
model.phase = 'test'
model.sampler.batch_size=100
examples_z = model.embed(examples, examples_y)
examples_recon = model.reconstruct(examples_z, examples_y)
recon_video.append(img_tile(to_b01c(examples_recon, img_shape)))
samples = model.reconstruct(samples_z, samples_y)
sample_video.append(img_tile(to_b01c(samples, img_shape)))
model.setup(**train_input.shapes)
model.phase = 'train'
# Train network
runs = [
(75, dp.RMSProp(learn_rate=0.075)),
(25, dp.RMSProp(learn_rate=0.05)),
(5, dp.RMSProp(learn_rate=0.01)),
(5, dp.RMSProp(learn_rate=0.005)),
]
try:
for n_epochs, learn_rule in runs:
if mode == 'vae':
vaegan.train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
else:
vaegan.margin_train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
except KeyboardInterrupt:
pass
raw_input('\n\nsave model to %s?\n' % filename)
with open(filename, 'wb') as f:
expressions = encoder, sampler, generator, discriminator
pickle.dump(expressions, f)
model.phase = 'test'
batch_size = 128
model.sampler.batch_size=128
z = []
i = 0
z = model.embed(x_train, y_train)
print(z.shape)
z_mean = np.mean(z, axis=0)
z_std = np.std(z, axis=0)
z_cov = np.cov(z.T)
print(np.mean(z_mean), np.std(z_mean))
print(np.mean(z_std), np.std(z_std))
print(z_mean.shape, z_std.shape, z_cov.shape)
raw_input('\n\ngenerate latent space video?\n')
print('Generating latent space video')
walk_video = Video('plots/mnist_' + experiment_name + '_walk.mp4')
for z in random_walk(samples_z, 500, n_dir_steps=10, mean=z_mean, std=z_cov):
samples = model.reconstruct(z, samples_y)
walk_video.append(img_tile(to_b01c(samples, img_shape)))
print('Generating AdversarialMNIST dataset')
_, y_train, _, y_test = dataset.arrays(dp_dtypes=True)
n = 0
batch_size = 512
advmnist_size = 1e6
x_advmnist = np.empty((advmnist_size, 28*28))
y_advmnist = np.empty((advmnist_size,))
while n < advmnist_size:
samples_z = np.random.multivariate_normal(mean=z_mean, cov=z_cov,
size=batch_size)
samples_z = samples_z.astype(dp.float_)
start_idx = n % len(y_train)
stop_idx = (n + batch_size) % len(y_train)
if start_idx > stop_idx:
samples_y = np.concatenate([y_train[start_idx:], y_train[:stop_idx]])
else:
samples_y = y_train[start_idx:stop_idx]
y_advmnist[n:n+batch_size] = samples_y[:advmnist_size-n]
samples_y = one_hot(samples_y, n_classes).astype(dp.float_)
samples = model.reconstruct(samples_z, samples_y)
x_advmnist[n:n+batch_size] = samples[:advmnist_size-n]
n += batch_size
x_train = x_advmnist
y_train = y_advmnist
import sklearn.neighbors
clf = sklearn.neighbors.KNeighborsClassifier(n_neighbors=1, algorithm='brute', n_jobs=-1)
clf.fit(x_train, y_train)
print('KNN predict')
step = 2500
errors = []
i = 0
while i < len(x_test):
print(i)
errors.append(clf.predict(x_test[i:i+step]) != y_test[i:i+step])
i += step
error = np.mean(errors)
print('Test error rate: %.4f' % error)
print('DONE ' + experiment_name)
def run():
mode = 'vaegan'
vae_grad_scale = 0.0001
kld_weight = 1.0
z_gan_prop = False
experiment_name = mode
experiment_name += '_scale%.1e' % vae_grad_scale
experiment_name += '_kld%.2f' % kld_weight
if z_gan_prop:
experiment_name += '_zprop'
filename = 'savestates/lfw_' + experiment_name + '.pickle'
in_filename = None
print('experiment_name', experiment_name)
print('in_filename', in_filename)
print('filename', filename)
# Fetch dataset
x_train = lfw.lfw_imgs(alignment='deepfunneled', size=64, crop=50,
shuffle=True)
img_shape = x_train.shape[1:]
# Normalize pixel intensities
scaler = dp.UniformScaler(low=-1, high=1)
x_train = scaler.fit_transform(x_train)
# Setup network
if in_filename is None:
print('Creating new model')
expressions = model_expressions(img_shape)
else:
print('Starting from %s' % in_filename)
with open(in_filename, 'rb') as f:
expressions = pickle.load(f)
encoder, sampler, generator, discriminator = expressions
model = vaegan.VAEGAN(
encoder=encoder,
sampler=sampler,
generator=generator,
discriminator=discriminator,
mode=mode,
vae_grad_scale=vae_grad_scale,
kld_weight=kld_weight,
)
# Prepare network inputs
batch_size = 64
train_input = dp.Input(x_train, batch_size=batch_size, epoch_size=250)
# Plotting
n_examples = 100
examples = x_train[:n_examples]
samples_z = np.random.normal(size=(n_examples, model.sampler.n_hidden))
samples_z = samples_z.astype(dp.float_)
recon_video = Video('plots/lfw_' + experiment_name + '_reconstruction.mp4')
sample_video = Video('plots/lfw_' + experiment_name + '_samples.mp4')
sp.misc.imsave('lfw_examples.png', img_tile(dp.misc.to_b01c(examples)))
def plot():
model.phase = 'test'
examples_z = model.embed(examples)
reconstructed = clip_range(model.reconstruct(examples_z))
recon_video.append(img_tile(dp.misc.to_b01c(reconstructed)))
z = model.embed(x_train)
z_mean = np.mean(z, axis=0)
z_std = np.std(z, axis=0)
model.hidden_std = z_std
z_std = np.diagflat(z_std)
samples_z = np.random.multivariate_normal(mean=z_mean, cov=z_std,
size=(n_examples,))
samples_z = samples_z.astype(dp.float_)
samples = clip_range(model.reconstruct(samples_z))
sample_video.append(img_tile(dp.misc.to_b01c(samples)))
model.phase = 'train'
model.setup(**train_input.shapes)
# Train network
runs = [
(150, dp.RMSProp(learn_rate=0.05)),
(250, dp.RMSProp(learn_rate=0.03)),
(100, dp.RMSProp(learn_rate=0.01)),
(15, dp.RMSProp(learn_rate=0.005)),
]
try:
import timeit
for n_epochs, learn_rule in runs:
if mode == 'vae':
vaegan.train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
else:
vaegan.margin_train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
except KeyboardInterrupt:
pass
raw_input('\n\nsave model to %s?\n' % filename)
with open(filename, 'wb') as f:
expressions = encoder, sampler, generator, discriminator
pickle.dump(expressions, f)
model.phase = 'test'
batch_size = 128
model.sampler.batch_size=128
z = model.embed(x_train)
z_mean = np.mean(z, axis=0)
z_std = np.std(z, axis=0)
z_cov = np.cov(z.T)
print(np.mean(z_mean), np.std(z_mean))
print(np.mean(z_std), np.std(z_std))
print(z_mean.shape, z_std.shape, z_cov.shape)
model.sampler.batch_size=100
samples_z = model.embed(examples)
print('Generating latent space video')
walk_video = Video('plots/lfw_' + experiment_name + '_walk.mp4')
for z in random_walk(samples_z, 500, n_dir_steps=10, mean=z_mean, std=z_cov):
samples = clip_range(model.reconstruct(z))
walk_video.append(img_tile(dp.misc.to_b01c(samples)))
def run():
mode = 'gan'
experiment_name = mode + '_stride_local_discrimination'
filename = 'savestates/cifar_cond_' + experiment_name + '.pickle'
in_filename = filename
in_filename = None
print('experiment_name', experiment_name)
print('in_filename', in_filename)
print('filename', filename)
# Fetch dataset
dataset = dp.dataset.CIFAR10()
x_train, y_train, x_test, y_test = dataset.arrays(dp_dtypes=True)
n_classes = dataset.n_classes
# Normalize pixel intensities
scaler = dp.StandardScaler()
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
y_train = one_hot(y_train, n_classes).astype(dp.float_)
y_test = one_hot(y_test, n_classes).astype(dp.float_)
# Setup network
if in_filename is None:
print('Creating new model')
img_shape = x_train.shape[1:]
expressions = model_expressions(img_shape)
else:
print('Starting from %s' % in_filename)
with open(in_filename, 'rb') as f:
expressions = pickle.load(f)
encoder, sampler, generator, discriminator = expressions
model = cond_vaegan.ConditionalVAEGAN(
encoder=encoder,
sampler=sampler,
generator=generator,
discriminator=discriminator,
mode=mode,
)
# Prepare network inputs
batch_size = 64
train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size,
epoch_size=150)
# Plotting
n_examples = 100
examples = x_test[:n_examples]
examples_y = y_test[:n_examples]
samples_z = np.random.normal(size=(n_examples, model.sampler.n_hidden))
samples_z = samples_z.astype(dp.float_)
samples_y = ((np.arange(n_examples) // 10) % n_classes)
samples_y = one_hot(samples_y, n_classes).astype(dp.float_)
recon_video = Video('plots/cifar_' + experiment_name +
'_reconstruction.mp4')
sample_video = Video('plots/cifar_' + experiment_name + '_samples.mp4')
sp.misc.imsave('cifar_examples.png', img_tile(dp.misc.to_b01c(examples)))
def plot():
examples_z = model.embed(examples, examples_y)
examples_recon = model.reconstruct(examples_z, examples_y)
examples_recon = clip_range(examples_recon)
recon_video.append(img_tile(dp.misc.to_b01c(examples_recon)))
samples = clip_range(model.reconstruct(samples_z, samples_y))
sample_video.append(img_tile(dp.misc.to_b01c(samples)))
model.setup(**train_input.shapes)
# Train network
runs = [
# (10, dp.RMSProp(learn_rate=0.08)),
# (25, dp.RMSProp(learn_rate=0.12)),
# (100, dp.RMSProp(learn_rate=0.1)),
(150, dp.RMSProp(learn_rate=0.075)),
(150, dp.RMSProp(learn_rate=0.06)),
(150, dp.RMSProp(learn_rate=0.05)),
(150, dp.RMSProp(learn_rate=0.04)),
(25, dp.RMSProp(learn_rate=0.01)),
]
try:
for n_epochs, learn_rule in runs:
if mode == 'vae':
vaegan.train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
else:
vaegan.margin_train(model, train_input, learn_rule, n_epochs,
epoch_callback=plot)
except KeyboardInterrupt:
pass
raw_input('\n\nsave model to %s?\n' % filename)
with open(filename, 'wb') as f:
expressions = encoder, sampler, generator, discriminator
pickle.dump(expressions, f)
print('Generating latent space video')
walk_video = Video('plots/cifar_' + experiment_name + '_walk.mp4')
for z in random_walk(samples_z, 500, step_std=0.15):
samples = clip_range(model.reconstruct(z, samples_y))
walk_video.append(img_tile(dp.misc.to_b01c(samples)))