def main(dataset_name, net_name, xp_path, data_path, load_config, load_model, objective, nu, device, seed,
optimizer_name, lr, n_epochs, lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name, ae_lr,
ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay, n_jobs_dataloader, normal_class):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' % cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' % (cfg.settings['ae_lr_milestone'],))
logger.info('Pretraining batch size: %d' % cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' % cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' % (cfg.settings['lr_milestone'],))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Plot most anomalous and most normal (within-class) test samples
indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(labels), np.array(scores)
idx_sorted = indices[labels == 0][np.argsort(scores[labels == 0])] # sorted from lowest to highest anomaly score
if dataset_name in ('mnist', 'cifar10'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted[:32], ...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted[-32:], ...].unsqueeze(1)
if dataset_name == 'cifar10':
X_normals = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...], (0, 3, 1, 2)))
X_outliers = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...], (0, 3, 1, 2)))
plot_images_grid(X_normals, export_img=xp_path + '/normals', title='Most normal examples', padding=2)
plot_images_grid(X_outliers, export_img=xp_path + '/outliers', title='Most anomalous examples', padding=2)
# Save results, model, and configuration
deep_SVDD.save_results(export_json=xp_path + '/results.json')
deep_SVDD.save_model(export_model=xp_path + '/model.tar')
cfg.save_config(export_json=xp_path + '/config.json')
def main(dataset_name, net_name, xp_path, data_path, load_config, load_model,
load_ae_model, objective, nu, number_clusters, device, seed,
optimizer_name, lr, n_epochs, lr_milestone, batch_size, weight_decay,
pretrain, ae_optimizer_name, ae_lr, ae_n_epochs, ae_lr_milestone,
ae_batch_size, ae_weight_decay, n_jobs_dataloader, normal_class):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
logger.info('Number of hyperphere centers: %d' %
cfg.settings['number_clusters'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(xp_path, cfg.settings['objective'],
cfg.settings['nu'], cfg.settings['number_clusters'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
# If specified, load pretrained AE model (autoencoder weights)
if load_ae_model:
deep_SVDD.load_pretrained_AE_model(model_path=load_ae_model)
logger.info('Loading pretrained AE model from %s.' % load_ae_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Save results, model, and configuration
deep_SVDD.save_results(export_json=xp_path + '/results.json')
if pretrain:
deep_SVDD.save_model(export_model=xp_path + '/model.tar')
else:
deep_SVDD.save_model(export_model=xp_path + '/model.tar',
save_ae=False)
cfg.save_config(export_json=xp_path + '/config.json')
# Save cluster centers
np.save(os.path.join(xp_path, 'centers.npy'), np.asarray(deep_SVDD.c))
# Plot most anomalous and most normal (within-class) test samples
indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(labels), np.array(
scores)
idx_sorted = indices[labels == 0][np.argsort(
scores[labels == 0])] # sorted from lowest to highest anomaly score
if dataset_name in ('mnist', 'cifar10', 'cycif'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted[:32],
...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted[-32:],
...].unsqueeze(1)
plot_images_grid(X_normals,
export_img=xp_path + '/normals',
title='Most normal examples',
padding=2)
plot_images_grid(X_outliers,
export_img=xp_path + '/outliers',
title='Most anomalous examples',
padding=2)
if dataset_name == 'cifar10':
X_normals = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...],
(0, 3, 1, 2)))
X_outliers = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...],
(0, 3, 1, 2)))
plot_images_grid(X_normals,
export_img=xp_path + '/normals',
title='Most normal examples',
padding=2)
plot_images_grid(X_outliers,
export_img=xp_path + '/outliers',
title='Most anomalous examples',
padding=2)
if dataset_name == 'cycif':
# # Lowest to highest uncertainty scores
# idx_sorted_all = indices[np.argsort(scores)]
# labels_sorted_all = labels[np.argsort(scores)]
# scores_sorted_all = np.sort(scores)
# for i in range(32):
# idx = idx_sorted_all[i]
# X = dataset.test_set[idx][0].unsqueeze(1)
# # From test images, extract the ones model predicts as normal with highest confidence (better)
# plot_images_labels(X, label = labels_sorted_all[i], export_img=xp_path + '/images/simple_img_'+str(i), title='Simplest Example: Score = {:4.2f}'.format(scores_sorted_all[i]), padding=2)
# # Highest to lowest uncertainty scores
# idx_sorted_all = np.flip(idx_sorted_all)
# labels_sorted_all = np.flip(labels_sorted_all)
# scores_sorted_all = np.flip(scores_sorted_all)
# for i in range(32):
# idx = idx_sorted_all[i]
# X = dataset.test_set[idx][0].unsqueeze(1)
# # From test images, extract the ones model predicts as normal with lowest confidence (worse)
# plot_images_labels(X, label = labels_sorted_all[i], export_img=xp_path + '/images/difficult_img_'+str(i), title='Difficult Example: Score = {:4.2f}'.format(scores_sorted_all[i]), padding=2)
# Lowest to highest uncertainty scores
idx_sorted_all = indices[np.argsort(scores)]
labels_sorted_all = labels[np.argsort(scores)]
scores_sorted_all = np.sort(scores)
for i in range(128):
idx = idx_sorted_all[i]
X = dataset.test_set[idx][0].unsqueeze(1)
plot_images_labels(
X,
label=labels_sorted_all[i],
export_img=xp_path + '/images/img_' + str(i),
title='Score = {:4.2f}'.format(scores_sorted_all[i]),
padding=2)
# Assemble Gallery
folder = xp_path + '/images'
image_paths = [
os.path.join(folder, f) for f in os.listdir(folder)
if f.endswith('.png')
]
# Random selection of images
image_array = random.sample(image_paths, k=128)
# Create and save image grid
image = concat_images(image_array, (100, 100), (16, 8))
image.save(os.path.join(folder, 'gallery_128.png'), 'PNG')
def main(dataset_name, net_name, xp_path, data_path, load_config, load_model,
objective, nu, device, seed, optimizer_name, lr, n_epochs,
lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name,
ae_lr, ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay,
n_jobs_dataloader, ae_loss_type, ae_only, normal_class, ae_test_only):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
mean = [
(0.36607818518032215, 0.3528722483374472, 0.3585191239764038), # 0
(0.4487305946663354, 0.4487305946663354, 0.4487305946663354), # 1
(0.3923340318128373, 0.26295472525674995, 0.22025334692657814), # 2
(0.4536255693657713, 0.4682865838881645, 0.4452575836280415), # 3
(0.672454086143443, 0.4779993567370712, 0.35007702036667776), # 4
(0.5352967021800805, 0.5314880132137422, 0.547828897157147), # 5
(0.3267409463643222, 0.41484389522093523, 0.46695618025405883), # 6
(0.6926364358307354, 0.662149771557822, 0.6490556404776292), # 7
(0.24011281595607017, 0.1769201147939173, 0.17123964257174726), # 8
(0.21251877631977975, 0.23440739849813622, 0.2363959074824541), # 9
(0.3025230547246622, 0.30300693821061303, 0.32466943588225744), # 10
(0.7214971293922232, 0.7214971293922232, 0.7214971293922232), # 11
(0.20453672401964704, 0.19061953742573437, 0.1973630989492544), # 12
(0.38709726938081024, 0.27680750921869235, 0.24161576675737736), # 13
(0.39719792798156195, 0.39719792798156195, 0.39719792798156195), # 14
]
std = [
(0.1334089197933497, 0.13091438558839882, 0.11854704285817017), # 0
(0.16192189716258867, 0.16192189716258867, 0.16192189716258867), # 1
(0.0527090063203568, 0.035927180158353854, 0.026535684323885065), # 2
(0.11774565267141425, 0.13039328961987165, 0.12533147519872007), # 3
(0.07714836895006975, 0.06278302787607731, 0.04349760909698915), # 4
(0.36582285759516936, 0.3661720233895615, 0.34943018535446296), # 5
(0.14995070226373788, 0.2117666336616603, 0.23554648659289779), # 6
(0.23612927993223184, 0.25644744015075704, 0.25718179933681784), # 7
(0.168789697373752, 0.07563237349131141, 0.043146545992581754), # 8
(0.15779873915363898, 0.18099161937329614, 0.15159372072430388), # 9
(0.15720102988319967, 0.1803989691876269, 0.15113407058442763), # 10
(0.13265686578689692, 0.13265686578689692, 0.13265686578689692), # 11
(0.2316392849251032, 0.21810285502082638, 0.19743939091294657), # 12
(0.20497542590257026, 0.14190994609091834, 0.11531548927488476), # 13
(0.3185215984033291, 0.3185215984033291, 0.3185215984033291), # 14
]
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
xp_path = xp_path + '/'
xp_path = xp_path + str(normal_class)
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %s' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
model_save_path = './models/' + dataset_name + '/' + str(
normal_class) + '_' + str(
ae_n_epochs) + '_' + ae_loss_type + '.pth'
if ae_test_only == False:
deep_SVDD.pretrain(
dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader,
dataset_name=dataset_name,
ae_loss_type=ae_loss_type,
ae_only=ae_only,
model_save_path=model_save_path)
else:
deep_SVDD.load_test(
dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader,
dataset_name=dataset_name,
ae_loss_type=ae_loss_type,
ae_only=ae_only,
model_save_path=model_save_path)
# Plot most anomalous and most normal (within-class) test samples
exit(0)
indices, labels, scores = zip(*deep_SVDD.results['ae_test_scores'])
indices, labels, scores = np.array(indices), np.array(
labels), np.array(scores)
idx_sorted = indices[labels == 0][np.argsort(scores[
labels == 0])] # sorted from lowest to highest anomaly score
if dataset_name in ('mnist', 'cifar10', 'object', 'texture'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted[:32],
...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted[-32:],
...].unsqueeze(1)
if dataset_name == 'cifar10':
X_normals = torch.tensor(
np.transpose(
dataset.test_set.test_data[idx_sorted[:32], ...],
(0, 3, 1, 2)))
X_outliers = torch.tensor(
np.transpose(
dataset.test_set.test_data[idx_sorted[-32:], ...],
(0, 3, 1, 2)))
if dataset_name == 'object':
# 22 3 256 256
X_normals = torch.tensor(dataset.test_data[idx_sorted[:32],
...])
X_outliers = torch.tensor(dataset.test_data[idx_sorted[-32:],
...])
for i in range(3):
X_normals[:, i, :, :] *= std[normal_class][i]
X_normals[:, i, :, :] += mean[normal_class][i]
X_outliers[:, i, :, :] *= std[normal_class][i]
X_outliers[:, i, :, :] += mean[normal_class][i]
#plot_images_grid(X_normals, export_img=xp_path + '/AE_normals', title='Most normal examples', padding=2)
#plot_images_grid(X_outliers, export_img=xp_path + '/AE_outliers', title='Most anomalous examples', padding=2)
if ae_only:
exit(0)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader,
dataset_name=dataset_name)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Plot most anomalous and most normal (within-class) test samples
indices, labels, scores, _, _ = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(labels), np.array(
scores)
idx_sorted = indices[labels == 0][np.argsort(
scores[labels == 0])] # sorted from lowest to highest anomaly score
if dataset_name in ('mnist', 'cifar10', 'object', 'texture'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted[:32],
...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted[-32:],
...].unsqueeze(1)
if dataset_name == 'cifar10':
X_normals = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...],
(0, 3, 1, 2)))
X_outliers = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...],
(0, 3, 1, 2)))
if dataset_name == 'object':
# 22 3 256 256
X_normals = torch.tensor(dataset.test_data[idx_sorted[:32], ...])
X_outliers = torch.tensor(dataset.test_data[idx_sorted[-32:], ...])
for i in range(3):
X_normals[:, i, :, :] *= std[normal_class][i]
X_normals[:, i, :, :] += mean[normal_class][i]
X_outliers[:, i, :, :] *= std[normal_class][i]
X_outliers[:, i, :, :] += mean[normal_class][i]
plot_images_grid(X_normals,
export_img=xp_path + '/normals',
title='Most normal examples',
padding=2)
plot_images_grid(X_outliers,
export_img=xp_path + '/outliers',
title='Most anomalous examples',
padding=2)
def main(dataset_name, net_name, xp_path, data_path, load_config, load_model,
objective, nu, device, seed, optimizer_name, lr, n_epochs,
lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name,
ae_lr, ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay,
n_jobs_dataloader, normal_class, save_points_outside_r):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=False)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
if save_points_outside_r:
logger.info('Saving points outside of r')
deep_SVDD.savePointsOutsideR(dataset,
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
deep_SVDD.save_results(export_json=xp_path + '/results.json')
deep_SVDD.save_model(export_model=xp_path + '/model.tar')
cfg.save_config(export_json=xp_path + '/config.json')
def main(dataset_name, net_name, xp_path, data_path, load_config, load_model,
objective, nu, device, seed, optimizer_name, lr, n_epochs,
lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name,
ae_lr, ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay,
n_jobs_dataloader, normal_class, img_name):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Current date and time
logger.info('Current date and time is %s.' % datetime.now())
# () arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-parameter: %.2f' % cfg.settings['nu'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Plot most anomalous and most normal (within-class) test samples
indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(labels), np.array(
scores)
idx_all_sorted = indices[np.argsort(scores)]
idx_normal_sorted = indices[labels == 0][np.argsort(
scores[labels == 0])] # sorted from lowest to highest anomaly score
idx_outlier_sorted = indices[labels == 1][np.argsort(scores[labels == 1])]
idx_sorted = indices[np.argsort(scores)]
test_auc = deep_SVDD.results['test_auc']
if dataset_name in ('mnist', 'cifar10', 'fashion', 'crack', 'crack128'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted_normal[:32],
...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted_normal[-32:],
...].unsqueeze(1)
if dataset_name == 'cifar10':
X_normals = torch.tensor(
np.transpose(
dataset.test_set.test_data[idx_sorted_normal[:32], ...],
(0, 3, 1, 2)))
X_outliers = torch.tensor(
np.transpose(
dataset.test_set.test_data[idx_sorted_normal[-32:], ...],
(0, 3, 1, 2)))
if dataset_name == 'fashion':
X_normals = torch.reshape(
torch.tensor(dataset.test_set.data[idx_sorted_normal[:32],
...]),
(32, 28, 28)).unsqueeze(1)
X_outliers = torch.reshape(
torch.tensor(dataset.test_set.data[idx_sorted_normal[-32:],
...]),
(32, 28, 28)).unsqueeze(1)
plot_imgs = True
indices, labels, scores = zip(
*deep_SVDD.results['test_scores (corner)'])
indices, labels, scores = np.array(indices), np.array(
labels), np.array(scores)
idx_all_sorted = indices[np.argsort(
scores)] # from lowest to highest score
idx_normal_sorted = indices[labels == 0][np.argsort(
scores[labels == 0])] # from lowest to highest score
idx_outlier_sorted = indices[labels == 1][np.argsort(
scores[labels == 1])] # from lowest to highest score
if dataset_name == 'crack':
mid = len(idx_all_sorted) / 2
if len(idx_all_sorted) > 64 and len(
idx_normal_sorted) > 64 and len(idx_outlier_sorted) > 100:
#X_middle = torch.reshape(torch.tensor(dataset.test_set.data[idx_all_sorted[int(mid-312):int(mid+313)], ...]), (625,64,64)).unsqueeze(1)
X_all_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[:64],
...]),
(64, 64, 64)).unsqueeze(1)
X_all_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[-144:],
...]),
(144, 64, 64)).unsqueeze(1)
X_normals_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[:64],
...]),
(64, 64, 64)).unsqueeze(1)
X_normals_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[-64:],
...]),
(64, 64, 64)).unsqueeze(1)
X_outliers_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[:100],
...]),
(100, 64, 64)).unsqueeze(1)
X_outliers_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[-100:],
...]),
(100, 64, 64)).unsqueeze(1)
else:
plot_imgs = False
X_all_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[:1], ...]),
(1, 64, 64)).unsqueeze(1)
X_all_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[-1:],
...]),
(1, 64, 64)).unsqueeze(1)
X_normals_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[:1],
...]),
(1, 64, 64)).unsqueeze(1)
X_normals_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[-1:],
...]),
(1, 64, 64)).unsqueeze(1)
X_outliers_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[:1],
...]),
(1, 64, 64)).unsqueeze(1)
X_outliers_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[-1:],
...]),
(1, 64, 64)).unsqueeze(1)
if dataset_name == 'crack128':
mid = len(idx_all_sorted) / 2
if len(idx_all_sorted) > 64 and len(
idx_normal_sorted) > 64 and len(idx_outlier_sorted) > 100:
#X_middle = torch.reshape(torch.tensor(dataset.test_set.data[idx_all_sorted[int(mid-312):int(mid+313)], ...]), (625,128,128)).unsqueeze(1)
X_all_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[:64],
...]),
(64, 128, 128)).unsqueeze(1)
X_all_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[-144:],
...]),
(144, 128, 128)).unsqueeze(1)
X_normals_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[:64],
...]),
(64, 128, 128)).unsqueeze(1)
X_normals_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[-64:],
...]),
(64, 128, 128)).unsqueeze(1)
X_outliers_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[:100],
...]),
(100, 128, 128)).unsqueeze(1)
X_outliers_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[-100:],
...]),
(100, 128, 128)).unsqueeze(1)
else:
plot_imgs = False
X_all_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[:1], ...]),
(1, 128, 128)).unsqueeze(1)
X_all_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_all_sorted[-1:],
...]),
(1, 128, 128)).unsqueeze(1)
X_normals_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[:1],
...]),
(1, 128, 128)).unsqueeze(1)
X_normals_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_normal_sorted[-1:],
...]),
(1, 128, 128)).unsqueeze(1)
X_outliers_normal = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[:1],
...]),
(1, 128, 128)).unsqueeze(1)
X_outliers_outlier = torch.reshape(
torch.tensor(
dataset.test_set_corner.data[idx_outlier_sorted[-1:],
...]),
(1, 128, 128)).unsqueeze(1)
if plot_imgs:
#plot_images_grid(X_middle, export_img=xp_path + '/plots/' + img_name + '_all_middle_', title='All samples', padding=2, nrow=25)
#plot_images_grid(X_all_normal, export_img=xp_path + '/plots/' + img_name + '_all_low_', title='Least anomalous samples', padding=2, nrow=8)
plot_images_grid(X_all_outlier,
export_img=xp_path + '/plots/' + img_name +
'_all_high_',
title='Most anomalous samples',
padding=2,
nrow=12)
#plot_images_grid(X_normals_normal, export_img=xp_path + '/plots/' + img_name + '_normals_low_', title='Least anomalous normal samples', padding=2, nrow=8)
plot_images_grid(X_normals_outlier,
export_img=xp_path + '/plots/' + img_name +
'_normals_high_',
title='Most anmalous normal samples',
padding=2,
nrow=8)
plot_images_grid(X_outliers_normal,
export_img=xp_path + '/plots/' + img_name +
'_outliers_low_',
title='Least anomalous anomaly samples',
padding=2,
nrow=10)
plot_images_grid(X_outliers_outlier,
export_img=xp_path + '/plots/' + img_name +
'_outliers_high_',
title='Most anomalous anomaly samples',
padding=2,
nrow=10)
test_auc = deep_SVDD.results['test_auc']
test_auc_corner = deep_SVDD.results['test_auc (corner)']
plot_images_hist(
scores[labels == 0],
scores[labels == 1],
export_img=xp_path + '/plots/' + img_name + '_hist_corner',
title=
'Deep SVDD Anomaly scores of normal and crack samples (with corner cracks)',
auc=test_auc_corner)
indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(
labels), np.array(scores)
plot_images_hist(
scores[labels == 0],
scores[labels == 1],
export_img=xp_path + '/plots/' + img_name + '_hist',
title='Deep SVDD anomaly scores of normal and crack samples',
auc=test_auc)
# Save results, model, and configuration
deep_SVDD.save_results(export_json=xp_path + '/results.json')
deep_SVDD.save_model(export_model=xp_path + '/model.tar')
cfg.save_config(export_json=xp_path + '/config.json')
def main(dataset_name, net_name, xp_path, data_path, load_data, load_config,
load_model, objective, nu, device, seed, optimizer_name, lr, n_epochs,
lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name,
ae_lr, ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay,
n_jobs_dataloader, normal_class):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural n etwork to use.
:arg XP_PATH: Export path for loggi ng the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
if dataset_name == 'campus':
train_path = 'train/OK'
test_path = 'test'
train_image, test_image, test_label = train_test_numpy_load(
data_path, train_path, test_path, load_data)
dataset = load_campus_dataset(dataset_name, data_path, train_image,
test_image, test_label)
else:
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
# logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader,
test_image=test_image)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# plot t_sne
# deep_SVDD.t_sne(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader, data_path=data_path, xp_path=xp_path)
# Test model
deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Plot most anomalous and most normal (within-class) test samples
indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
indices, labels, scores = np.array(indices), np.array(labels), np.array(
scores)
if dataset_name in ('mnist', 'cifar10', 'campus'):
if dataset_name == 'mnist':
X_normals = dataset.test_set.test_data[idx_sorted[:32],
...].unsqueeze(1)
X_outliers = dataset.test_set.test_data[idx_sorted[-32:],
...].unsqueeze(1)
if dataset_name == 'cifar10':
X_normals = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...],
(0, 3, 1, 2)))
X_outliers = torch.tensor(
np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...],
(0, 3, 1, 2)))
if dataset_name == 'campus':
test_score_path = os.path.join(xp_path, 'test_score.pickle')
with open(test_score_path, 'wb') as f:
pickle.dump(deep_SVDD.results['test_scores'], f,
pickle.HIGHEST_PROTOCOL)
if dataset_name == 'campus':
fpr = dict()
tpr = dict()
roc_auc = dict()
fpr, tpr, threshold = roc_curve(labels, scores)
roc_auc = auc(fpr, tpr)
plt.figure()
lw = 2
plt.plot(fpr,
tpr,
color='darkorange',
lw=lw,
label='ROC curve (area= %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic example')
plt.legend(loc="lower right")
plt.savefig(os.path.join(xp_path, 'auc_roc.png'))
else:
plot_images_grid(X_normals,
export_img=xp_path + '/normals',
title='Most normal examples',
padding=2)
plot_images_grid(X_outliers,
export_img=xp_path + '/outliers',
title='Most anomalous examples',
padding=2)
# Save results, model, and configuration
deep_SVDD.save_results(export_json=xp_path + '/results.json')
deep_SVDD.save_model(export_model=xp_path + '/model.tar')
cfg.save_config(export_json=xp_path + '/config.json')
def main(dataset_name, net_name, xp_path, data_path, load_config, load_model, objective, nu, focal_parameter, update_center_epochs, device, seed,
optimizer_name, lr, n_epochs, lr_milestone, batch_size, weight_decay, pretrain, ae_optimizer_name, ae_lr,
ae_n_epochs, ae_lr_milestone, ae_batch_size, ae_weight_decay, n_jobs_dataloader, normal_class):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Data path is %s.' % data_path)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
logger.info('focal_parameter: %.2f' % cfg.settings['focal_parameter'])
logger.info('update_center_epochs: %d' % cfg.settings['update_center_epochs'])
# Set seed
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
os.environ['PYTHONHASHSEED'] = str(seed)
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
torch.cuda.manual_seed(cfg.settings['seed'])
torch.cuda.manual_seed_all(cfg.settings['seed'])
cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, data_path, normal_class)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'], cfg.settings['focal_parameter'], cfg.settings['update_center_epochs'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' % cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' % cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' % cfg.settings['ae_n_epochs'])
logger.info('Pretraining learning rate scheduler milestones: %s' % (cfg.settings['ae_lr_milestone'],))
logger.info('Pretraining batch size: %d' % cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' % cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' % cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' % (cfg.settings['lr_milestone'],))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' % cfg.settings['weight_decay'])
# record test AUC after each 100 epoch
# f_get_para = open('../log/mnist_test/100_AUC.txt', 'w')
# f_get_para.write("\r\n \r\nrecord test AUC each 100 epoch \r\n \r\n \r\n")
# f_get_para.close()
#
# f_get_para = open('../log/mnist_test/get_param.txt', 'w')
# f_get_para.write("\r\n \r\nrecord test AUC each very epoch \r\n \r\n \r\n")
# f_get_para.close()
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
# deep_SVDD.test(dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
# Plot most anomalous and most normal (within-class) test samples
# indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
# indices, labels, scores = np.array(indices), np.array(labels), np.array(scores)
# idx_sorted = indices[labels == 0][np.argsort(scores[labels == 0])] # sorted from lowest to highest anomaly score
#
# if dataset_name in ('mnist', 'cifar10'):
#
# if dataset_name == 'mnist':
# X_normals = dataset.test_set.test_data[idx_sorted[:32], ...].unsqueeze(1)
# X_outliers = dataset.test_set.test_data[idx_sorted[-32:], ...].unsqueeze(1)
#
# if dataset_name == 'cifar10':
# X_normals = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...], (0, 3, 1, 2)))
# X_outliers = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...], (0, 3, 1, 2)))
#
# plot_images_grid(X_normals, export_img=xp_path + '/normals', title='Most normal examples', padding=2)
# plot_images_grid(X_outliers, export_img=xp_path + '/outliers', title='Most anomalous examples', padding=2)
#
# # Save results, model, and configuration
# deep_SVDD.save_results(export_json=xp_path + '/results.json')
# deep_SVDD.save_model(export_model=xp_path + '/model.tar')
# cfg.save_config(export_json=xp_path + '/config.json')
# plot curves
loss_plot = deep_SVDD.trainer.Loss_list
accuracy_plot = deep_SVDD.trainer.Accuracy_list
x1 = range(0, n_epochs)
y1 = accuracy_plot
x2 = range(0, n_epochs)
y2 = loss_plot
plt.subplot(2, 1, 1)
plt.plot(x1, y1, 'o-')
plt.title('Class %d vs focal %.2f' % (normal_class, focal_parameter))
plt.ylabel('Test accuracy')
plt.subplot(2, 1, 2)
plt.plot(x2, y2, '.-')
plt.xlabel('Test loss vs. epoches')
plt.ylabel('Test loss')
plt.savefig("accuracy_loss focal %.2f .jpg" % focal_parameter)
def main(dataset_name, net_name, load_config, load_model, objective, nu,
device, seed, optimizer_name, lr, n_epochs, lr_milestone, batch_size,
weight_decay, pretrain, ae_optimizer_name, ae_lr, ae_n_epochs,
ae_lr_milestone, ae_batch_size, ae_weight_decay, n_jobs_dataloader,
ratio, run_times):
"""
Deep SVDD, a fully deep method for anomaly detection.
:arg DATASET_NAME: Name of the dataset to load.
:arg NET_NAME: Name of the neural network to use.
:arg XP_PATH: Export path for logging the experiment.
:arg DATA_PATH: Root path of data.
"""
class_num = 10
if dataset_name == 'cifar100':
class_num = 20
for run_index in range(run_times):
#for ratio in [0.05, 0.1, 0.15, 0.2, 0.25]:
for i in range(class_num):
normal_class = i
class_name = get_class_name_from_index(normal_class, dataset_name)
os.makedirs(os.path.join(RESULTS_DIR), exist_ok=True)
# Get configuration
cfg = Config(locals().copy())
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger()
logger.setLevel(logging.INFO)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
xp_path = RESULTS_DIR
log_file = xp_path + '/log.txt'
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(logging.INFO)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
# Print arguments
logger.info('Log file is %s.' % log_file)
logger.info('Export path is %s.' % xp_path)
logger.info('Dataset: %s' % dataset_name)
logger.info('Normal class: %d' % normal_class)
logger.info('Network: %s' % net_name)
# If specified, load experiment config from JSON-file
if load_config:
cfg.load_config(import_json=load_config)
logger.info('Loaded configuration from %s.' % load_config)
# Print configuration
logger.info('Deep SVDD objective: %s' % cfg.settings['objective'])
logger.info('Nu-paramerter: %.2f' % cfg.settings['nu'])
# Set seed
cfg.settings['seed'] = run_index
if cfg.settings['seed'] != -1:
random.seed(cfg.settings['seed'])
np.random.seed(cfg.settings['seed'])
torch.manual_seed(cfg.settings['seed'])
logger.info('Set seed to %d.' % cfg.settings['seed'])
# Default device to 'cpu' if cuda is not available
if not torch.cuda.is_available():
device = 'cpu'
logger.info('Computation device: %s' % device)
logger.info('Number of dataloader workers: %d' % n_jobs_dataloader)
# Load data
dataset = load_dataset(dataset_name, normal_class, ratio)
# Initialize DeepSVDD model and set neural network \phi
deep_SVDD = DeepSVDD(cfg.settings['objective'], cfg.settings['nu'])
deep_SVDD.set_network(net_name)
# If specified, load Deep SVDD model (radius R, center c, network weights, and possibly autoencoder weights)
if load_model:
deep_SVDD.load_model(model_path=load_model, load_ae=True)
logger.info('Loading model from %s.' % load_model)
logger.info('Pretraining: %s' % pretrain)
if pretrain:
# Log pretraining details
logger.info('Pretraining optimizer: %s' %
cfg.settings['ae_optimizer_name'])
logger.info('Pretraining learning rate: %g' %
cfg.settings['ae_lr'])
logger.info('Pretraining epochs: %d' %
cfg.settings['ae_n_epochs'])
logger.info(
'Pretraining learning rate scheduler milestones: %s' %
(cfg.settings['ae_lr_milestone'], ))
logger.info('Pretraining batch size: %d' %
cfg.settings['ae_batch_size'])
logger.info('Pretraining weight decay: %g' %
cfg.settings['ae_weight_decay'])
# Pretrain model on dataset (via autoencoder)
deep_SVDD.pretrain(
dataset,
optimizer_name=cfg.settings['ae_optimizer_name'],
lr=cfg.settings['ae_lr'],
n_epochs=cfg.settings['ae_n_epochs'],
lr_milestones=cfg.settings['ae_lr_milestone'],
batch_size=cfg.settings['ae_batch_size'],
weight_decay=cfg.settings['ae_weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Log training details
logger.info('Training optimizer: %s' %
cfg.settings['optimizer_name'])
logger.info('Training learning rate: %g' % cfg.settings['lr'])
logger.info('Training epochs: %d' % cfg.settings['n_epochs'])
logger.info('Training learning rate scheduler milestones: %s' %
(cfg.settings['lr_milestone'], ))
logger.info('Training batch size: %d' % cfg.settings['batch_size'])
logger.info('Training weight decay: %g' %
cfg.settings['weight_decay'])
# Train model on dataset
deep_SVDD.train(dataset,
optimizer_name=cfg.settings['optimizer_name'],
lr=cfg.settings['lr'],
n_epochs=cfg.settings['n_epochs'],
lr_milestones=cfg.settings['lr_milestone'],
batch_size=cfg.settings['batch_size'],
weight_decay=cfg.settings['weight_decay'],
device=device,
n_jobs_dataloader=n_jobs_dataloader)
# Test model
scores, labels = deep_SVDD.test(
dataset, device=device, n_jobs_dataloader=n_jobs_dataloader)
res_file_name = '{}_dsvdd-{}_{}_{}.npz'.format(
dataset_name, ratio, class_name,
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name,
res_file_name)
os.makedirs(os.path.join(RESULTS_DIR, dataset_name), exist_ok=True)
save_roc_pr_curve_data(scores, labels, res_file_path)
# Plot most anomalous and most normal (within-class) test samples
# indices, labels, scores = zip(*deep_SVDD.results['test_scores'])
# indices, labels, scores = np.array(indices), np.array(labels), np.array(scores)
# idx_sorted = indices[labels == 0][np.argsort(scores[labels == 0])] # sorted from lowest to highest anomaly score
#
# if dataset_name in ('mnist', 'cifar10'):
#
# if dataset_name == 'mnist':
# X_normals = dataset.test_set.test_data[idx_sorted[:32], ...].unsqueeze(1)
# X_outliers = dataset.test_set.test_data[idx_sorted[-32:], ...].unsqueeze(1)
#
# if dataset_name == 'cifar10':
# X_normals = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[:32], ...], (0, 3, 1, 2)))
# X_outliers = torch.tensor(np.transpose(dataset.test_set.test_data[idx_sorted[-32:], ...], (0, 3, 1, 2)))
#
# plot_images_grid(X_normals, export_img=xp_path + '/normals', title='Most normal examples', padding=2)
# plot_images_grid(X_outliers, export_img=xp_path + '/outliers', title='Most anomalous examples', padding=2)
# Save results, model, and configuration
logger.info('finish class {} training.'.format(class_name))
logger.info('send exp finish mail.')
send_mailgun()