def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(
np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
images = tf.placeholder(tf.float32,
shape=(None, gen_image_size, gen_image_size,
3),
name='input')
# Normalize
images_norm = (images - img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(
images_norm, (gen_image_size, gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance / 2)
latent_var = mean + epsilon * std
# Create decoder
reconstructed_norm = vae.decoder(latent_var, False)
# Un-normalize
reconstructed = (reconstructed_norm * img_stddev) + img_mean
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
vae_checkpoint = os.path.expanduser(args.vae_checkpoint)
print('Restoring VAE checkpoint: %s' % vae_checkpoint)
saver.restore(sess, vae_checkpoint)
filename = os.path.expanduser(args.attributes_filename)
with h5py.File(filename, 'r') as f:
latent_vars = np.array(f.get('latent_vars'))
attributes = np.array(f.get('attributes'))
#fields = np.array(f.get('fields'))
attribute_vectors = np.array(f.get('attribute_vectors'))
# Reconstruct faces while adding varying amount of the selected attribute vector
attribute_index = 31 # 31: 'Smiling'
image_indices = [
8, 11, 13, 18, 19, 26, 31, 39, 47, 54, 56, 57, 58, 59, 60, 73
]
nrof_images = len(image_indices)
nrof_interp_steps = 10
sweep_latent_var = np.zeros(
(nrof_interp_steps * nrof_images, args.latent_var_size),
np.float32)
for j in range(nrof_images):
image_index = image_indices[j]
idx = np.argwhere(
attributes[:, attribute_index] == -1)[image_index, 0]
for i in range(nrof_interp_steps):
sweep_latent_var[i + nrof_interp_steps * j, :] = latent_vars[
idx, :] + 5.0 * i / nrof_interp_steps * attribute_vectors[
attribute_index, :]
recon = sess.run(reconstructed,
feed_dict={latent_var: sweep_latent_var})
img = facenet.put_images_on_grid(
recon,
shape=(nrof_interp_steps * 2, int(math.ceil(nrof_images / 2))))
image_filename = os.path.expanduser(args.output_image_filename)
print('Writing generated image to %s' % image_filename)
misc.imsave(image_filename, img)
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(
np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
log_file_name = os.path.join(model_dir, 'logs.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args,
os.path.join(model_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, model_dir, ' '.join(sys.argv))
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
train_set = facenet.get_dataset(args.data_dir)
image_list, _ = facenet.get_image_paths_and_labels(train_set)
# Create the input queue
input_queue = tf.train.string_input_producer(image_list, shuffle=True)
nrof_preprocess_threads = 4
image_per_thread = []
for _ in range(nrof_preprocess_threads):
file_contents = tf.read_file(input_queue.dequeue())
image = tf.image.decode_image(file_contents, channels=3)
image = tf.image.resize_image_with_crop_or_pad(
image, args.input_image_size, args.input_image_size)
image.set_shape((args.input_image_size, args.input_image_size, 3))
image = tf.cast(image, tf.float32)
#pylint: disable=no-member
image_per_thread.append([image])
images = tf.train.batch_join(image_per_thread,
batch_size=args.batch_size,
capacity=4 * nrof_preprocess_threads *
args.batch_size,
allow_smaller_final_batch=False)
# Normalize
images_norm = (images - img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(
images_norm, (gen_image_size, gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance / 2)
latent_var = mean + epsilon * std
# Create decoder network
reconstructed_norm = vae.decoder(latent_var, True)
# Un-normalize
reconstructed = (reconstructed_norm * img_stddev) + img_mean
# Create reconstruction loss
if args.reconstruction_loss_type == 'PLAIN':
images_resize = tf.image.resize_images(
images, (gen_image_size, gen_image_size))
reconstruction_loss = tf.reduce_mean(
tf.reduce_sum(tf.pow(images_resize - reconstructed, 2)))
elif args.reconstruction_loss_type == 'PERCEPTUAL':
network = importlib.import_module(args.model_def)
reconstructed_norm_resize = tf.image.resize_images(
reconstructed_norm,
(args.input_image_size, args.input_image_size))
# Stack images from both the input batch and the reconstructed batch in a new tensor
shp = [-1] + images_norm.get_shape().as_list()[1:]
input_images = tf.reshape(
tf.stack([images_norm, reconstructed_norm_resize], axis=0),
shp)
_, end_points = network.inference(input_images,
1.0,
phase_train=False,
bottleneck_layer_size=128,
weight_decay=0.0)
# Get a list of feature names to use for loss terms
feature_names = args.loss_features.replace(' ', '').split(',')
# Calculate L2 loss between original and reconstructed images in feature space
reconstruction_loss_list = []
for feature_name in feature_names:
feature_flat = slim.flatten(end_points[feature_name])
image_feature, reconstructed_feature = tf.unstack(tf.reshape(
feature_flat, [2, args.batch_size, -1]),
num=2,
axis=0)
reconstruction_loss = tf.reduce_mean(tf.reduce_sum(
tf.pow(image_feature - reconstructed_feature, 2)),
name=feature_name +
'_loss')
reconstruction_loss_list.append(reconstruction_loss)
# Sum up the losses in for the different features
reconstruction_loss = tf.add_n(reconstruction_loss_list,
'reconstruction_loss')
else:
pass
# Create KL divergence loss
kl_loss = kl_divergence_loss(mean, log_variance)
kl_loss_mean = tf.reduce_mean(kl_loss)
total_loss = args.alfa * kl_loss_mean + args.beta * reconstruction_loss
learning_rate = tf.train.exponential_decay(
args.initial_learning_rate,
global_step,
args.learning_rate_decay_steps,
args.learning_rate_decay_factor,
staircase=True)
# Calculate gradients and make sure not to include parameters for the perceptual loss model
opt = tf.train.AdamOptimizer(learning_rate)
grads = opt.compute_gradients(total_loss,
var_list=get_variables_to_train())
# Apply gradients
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
with tf.control_dependencies([apply_gradient_op]):
train_op = tf.no_op(name='train')
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
facenet_saver = tf.train.Saver(get_facenet_variables_to_restore())
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.compat.v1.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.reconstruction_loss_type == 'PERCEPTUAL':
if not args.pretrained_model:
raise ValueError(
'A pretrained model must be specified when using perceptual loss'
)
pretrained_model_exp = os.path.expanduser(
args.pretrained_model)
print('Restoring pretrained model: %s' % pretrained_model_exp)
facenet_saver.restore(sess, pretrained_model_exp)
log = {
'total_loss': np.zeros((0, ), np.float),
'reconstruction_loss': np.zeros((0, ), np.float),
'kl_loss': np.zeros((0, ), np.float),
'learning_rate': np.zeros((0, ), np.float),
}
step = 0
print('Running training')
while step < args.max_nrof_steps:
start_time = time.time()
step += 1
save_state = step > 0 and (step % args.save_every_n_steps == 0
or step == args.max_nrof_steps)
if save_state:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_, rec_ = sess.run(
[
train_op, reconstruction_loss, kl_loss_mean,
total_loss, learning_rate, reconstructed
])
img = facenet.put_images_on_grid(rec_, shape=(16, 8))
misc.imsave(
os.path.join(model_dir,
'reconstructed_%06d.png' % step), img)
else:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_ = sess.run(
[
train_op, reconstruction_loss, kl_loss_mean,
total_loss, learning_rate
])
log['total_loss'] = np.append(log['total_loss'], total_loss_)
log['reconstruction_loss'] = np.append(
log['reconstruction_loss'], reconstruction_loss_)
log['kl_loss'] = np.append(log['kl_loss'], kl_loss_mean_)
log['learning_rate'] = np.append(log['learning_rate'],
learning_rate_)
duration = time.time() - start_time
print(
'Step: %d \tTime: %.3f \trec_loss: %.3f \tkl_loss: %.3f \ttotal_loss: %.3f'
% (step, duration, reconstruction_loss_, kl_loss_mean_,
total_loss_))
if save_state:
print('Saving checkpoint file')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess,
checkpoint_path,
global_step=step,
write_meta_graph=False)
print('Saving log')
with h5py.File(log_file_name, 'w') as f:
for key, value in iteritems(log):
f.create_dataset(key, data=value)
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(
np.array([3941.30175781, 2856.94287109, 2519.35791016])
)
vae_checkpoint = os.path.expanduser(args.vae_checkpoint)
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
with tf.Graph().as_default():
filename = args.image
# Read image and convert to 3 channels
image = Image.open(filename)
image = image.convert('RGB')
image = image.resize((gen_image_size, gen_image_size), Image.ANTIALIAS)
image = np.array(image).reshape(1, gen_image_size, gen_image_size, 3)
images = tf.placeholder(
tf.float32,
shape=(None, gen_image_size, gen_image_size, 3),
name='input'
)
# Normalize
images_norm = (images - img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(
images_norm, (gen_image_size, gen_image_size)
)
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance / 2)
latent_var = mean + epsilon * std
# Create decoder
reconstructed_norm = vae.decoder(latent_var, False)
# Un-normalize
reconstructed = (reconstructed_norm * img_stddev) + img_mean
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction
)
sess = tf.Session(
config=tf.ConfigProto(
gpu_options=gpu_options,
log_device_placement=False
)
)
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
# coord = tf.train.Coordinator()
# tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if vae_checkpoint:
print('Restoring VAE checkpoint: %s' % vae_checkpoint)
saver.restore(sess, vae_checkpoint)
start_time = time.time()
latent_var_ = sess.run(latent_var, feed_dict={images: image})
duration = time.time() - start_time
print('Sess run: %.3f seconds' % duration)
# NOTE: This will print the 'Out of range' warning if the last
# batch is not full, as described by
# https://github.com/tensorflow/tensorflow/issues/8330
print('Got latent var shape {}'.format(latent_var_.shape))
# Reconstruct faces while adding varying amount of
# the selected attribute vector
attribute_index = 31 # 31: 'Smiling'
with h5py.File(args.attributes_filename, 'r') as f:
# latent_vars = np.array(f.get('latent_vars'))
# attributes = np.array(f.get('attributes'))
# fields = np.array(f.get('fields'))
attribute_vectors = np.array(f.get('attribute_vectors'))
nrof_interp_steps = 10
sweep_latent_var = np.zeros(
(nrof_interp_steps, latent_var.shape[1]), np.float32
)
for i in range(nrof_interp_steps):
sweep_latent_var[i, :] = (
latent_var_[0, :] + 5.0 * i /
nrof_interp_steps * attribute_vectors[attribute_index, :]
)
print('Reconstruct image')
start_time = time.time()
recon = sess.run(
reconstructed,
feed_dict={latent_var: sweep_latent_var}
)
duration = time.time() - start_time
print('Sess run: %.3f seconds' % duration)
img = facenet.put_images_on_grid(
recon, shape=(nrof_interp_steps, int(math.ceil(1 / 2)))
)
image_filename = os.path.expanduser(args.output_image_filename)
print('Writing generated image to %s' % image_filename)
misc.imsave(image_filename, img)
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
log_file_name = os.path.join(model_dir, 'logs.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(model_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, model_dir, ' '.join(sys.argv))
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
train_set = facenet.get_dataset(args.data_dir)
image_list, _ = facenet.get_image_paths_and_labels(train_set)
# Create the input queue
input_queue = tf.train.string_input_producer(image_list, shuffle=True)
nrof_preprocess_threads = 4
image_per_thread = []
for _ in range(nrof_preprocess_threads):
file_contents = tf.read_file(input_queue.dequeue())
image = tf.image.decode_image(file_contents, channels=3)
image = tf.image.resize_image_with_crop_or_pad(image, args.input_image_size, args.input_image_size)
image.set_shape((args.input_image_size, args.input_image_size, 3))
image = tf.cast(image, tf.float32)
#pylint: disable=no-member
image_per_thread.append([image])
images = tf.train.batch_join(
image_per_thread, batch_size=args.batch_size,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=False)
# Normalize
images_norm = (images-img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(images_norm, (gen_image_size,gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance/2)
latent_var = mean + epsilon * std
# Create decoder network
reconstructed_norm = vae.decoder(latent_var, True)
# Un-normalize
reconstructed = (reconstructed_norm*img_stddev) + img_mean
# Create reconstruction loss
if args.reconstruction_loss_type=='PLAIN':
images_resize = tf.image.resize_images(images, (gen_image_size,gen_image_size))
reconstruction_loss = tf.reduce_mean(tf.reduce_sum(tf.pow(images_resize - reconstructed,2)))
elif args.reconstruction_loss_type=='PERCEPTUAL':
network = importlib.import_module(args.model_def)
reconstructed_norm_resize = tf.image.resize_images(reconstructed_norm, (args.input_image_size,args.input_image_size))
# Stack images from both the input batch and the reconstructed batch in a new tensor
shp = [-1] + images_norm.get_shape().as_list()[1:]
input_images = tf.reshape(tf.stack([images_norm, reconstructed_norm_resize], axis=0), shp)
_, end_points = network.inference(input_images, 1.0,
phase_train=False, bottleneck_layer_size=128, weight_decay=0.0)
# Get a list of feature names to use for loss terms
feature_names = args.loss_features.replace(' ', '').split(',')
# Calculate L2 loss between original and reconstructed images in feature space
reconstruction_loss_list = []
for feature_name in feature_names:
feature_flat = slim.flatten(end_points[feature_name])
image_feature, reconstructed_feature = tf.unstack(tf.reshape(feature_flat, [2,args.batch_size,-1]), num=2, axis=0)
reconstruction_loss = tf.reduce_mean(tf.reduce_sum(tf.pow(image_feature-reconstructed_feature, 2)), name=feature_name+'_loss')
reconstruction_loss_list.append(reconstruction_loss)
# Sum up the losses in for the different features
reconstruction_loss = tf.add_n(reconstruction_loss_list, 'reconstruction_loss')
else:
pass
# Create KL divergence loss
kl_loss = kl_divergence_loss(mean, log_variance)
kl_loss_mean = tf.reduce_mean(kl_loss)
total_loss = args.alfa*kl_loss_mean + args.beta*reconstruction_loss
learning_rate = tf.train.exponential_decay(args.initial_learning_rate, global_step,
args.learning_rate_decay_steps, args.learning_rate_decay_factor, staircase=True)
# Calculate gradients and make sure not to include parameters for the perceptual loss model
opt = tf.train.AdamOptimizer(learning_rate)
grads = opt.compute_gradients(total_loss, var_list=get_variables_to_train())
# Apply gradients
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
with tf.control_dependencies([apply_gradient_op]):
train_op = tf.no_op(name='train')
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
facenet_saver = tf.train.Saver(get_facenet_variables_to_restore())
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.reconstruction_loss_type=='PERCEPTUAL':
if not args.pretrained_model:
raise ValueError('A pretrained model must be specified when using perceptual loss')
pretrained_model_exp = os.path.expanduser(args.pretrained_model)
print('Restoring pretrained model: %s' % pretrained_model_exp)
facenet_saver.restore(sess, pretrained_model_exp)
log = {
'total_loss': np.zeros((0,), np.float),
'reconstruction_loss': np.zeros((0,), np.float),
'kl_loss': np.zeros((0,), np.float),
'learning_rate': np.zeros((0,), np.float),
}
step = 0
print('Running training')
while step < args.max_nrof_steps:
start_time = time.time()
step += 1
save_state = step>0 and (step % args.save_every_n_steps==0 or step==args.max_nrof_steps)
if save_state:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_, rec_ = sess.run(
[train_op, reconstruction_loss, kl_loss_mean, total_loss, learning_rate, reconstructed])
img = facenet.put_images_on_grid(rec_, shape=(16,8))
misc.imsave(os.path.join(model_dir, 'reconstructed_%06d.png' % step), img)
else:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_ = sess.run(
[train_op, reconstruction_loss, kl_loss_mean, total_loss, learning_rate])
log['total_loss'] = np.append(log['total_loss'], total_loss_)
log['reconstruction_loss'] = np.append(log['reconstruction_loss'], reconstruction_loss_)
log['kl_loss'] = np.append(log['kl_loss'], kl_loss_mean_)
log['learning_rate'] = np.append(log['learning_rate'], learning_rate_)
duration = time.time() - start_time
print('Step: %d \tTime: %.3f \trec_loss: %.3f \tkl_loss: %.3f \ttotal_loss: %.3f' % (step, duration, reconstruction_loss_, kl_loss_mean_, total_loss_))
if save_state:
print('Saving checkpoint file')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step, write_meta_graph=False)
print('Saving log')
with h5py.File(log_file_name, 'w') as f:
for key, value in log.iteritems():
f.create_dataset(key, data=value)
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
images = tf.placeholder(tf.float32, shape=(None,gen_image_size,gen_image_size,3), name='input')
# Normalize
images_norm = (images-img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(images_norm, (gen_image_size,gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance/2)
latent_var = mean + epsilon * std
# Create decoder
reconstructed_norm = vae.decoder(latent_var, False)
# Un-normalize
reconstructed = (reconstructed_norm*img_stddev) + img_mean
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
vae_checkpoint = os.path.expanduser(args.vae_checkpoint)
print('Restoring VAE checkpoint: %s' % vae_checkpoint)
saver.restore(sess, vae_checkpoint)
filename = os.path.expanduser(args.attributes_filename)
with h5py.File(filename,'r') as f:
latent_vars = np.array(f.get('latent_vars'))
attributes = np.array(f.get('attributes'))
#fields = np.array(f.get('fields'))
attribute_vectors = np.array(f.get('attribute_vectors'))
# Reconstruct faces while adding varying amount of the selected attribute vector
attribute_index = 31 # 31: 'Smiling'
image_indices = [8,11,13,18,19,26,31,39,47,54,56,57,58,59,60,73]
nrof_images = len(image_indices)
nrof_interp_steps = 10
sweep_latent_var = np.zeros((nrof_interp_steps*nrof_images, args.latent_var_size), np.float32)
for j in range(nrof_images):
image_index = image_indices[j]
idx = np.argwhere(attributes[:,attribute_index]==-1)[image_index,0]
for i in range(nrof_interp_steps):
sweep_latent_var[i+nrof_interp_steps*j,:] = latent_vars[idx,:] + 5.0*i/nrof_interp_steps*attribute_vectors[attribute_index,:]
recon = sess.run(reconstructed, feed_dict={latent_var:sweep_latent_var})
img = facenet.put_images_on_grid(recon, shape=(nrof_interp_steps*2,int(math.ceil(nrof_images/2))))
image_filename = os.path.expanduser(args.output_image_filename)
print('Writing generated image to %s' % image_filename)
misc.imsave(image_filename, img)
