def compute_average_pr_auc(algo_name, results_dir, dataset_name, n_classes, positive='normal'):
results = {}
avg_results = []
std_results = []
if positive == 'inliers':
target = 'pr_auc_norm'
elif positive == 'outliers':
target = 'pr_auc_anom'
else:
raise KeyError(positive)
for c in range(n_classes):
class_name = get_class_name_from_index(c, dataset_name)
filenames = get_filenames(algo_name, results_dir, dataset_name, class_name)
results[class_name] = [np.load(f)[target] for f in filenames]
for k, v in results.items():
print('{}: {:.4f} +- {:.4f}'.format(k, np.mean(v), np.std(v)))
avg_results.append(np.mean(v))
std_results.append(np.std(v))
# compute the std of average results over multiple runs
min_runs = min([len(v) for v in results.values()])
std_rec = []
for i in range(min_runs):
ith_run = [results[get_class_name_from_index(c, dataset_name)][i] for c in range(n_classes)]
std_rec.append(np.mean(ith_run))
print('-------------------------------------------')
print('Average: {:.4f} +- {:.4f}'.format(np.mean(avg_results), np.std(std_rec)))
print('Formated:')
for r, s in zip(avg_results, std_results):
print('{:.4f}~{:.4f}'.format(r, s))
print('{:.4f}~{:.4f}'.format(np.mean(avg_results), np.std(std_rec)))
def compute_average_roc_auc(algo_name, results_dir, dataset_name, n_classes):
results = {}
avg_results = []
std_results = []
for c in range(n_classes):
class_name = get_class_name_from_index(c, dataset_name)
filenames = get_filenames(algo_name, results_dir, dataset_name,
class_name)
results[class_name] = [np.load(f)['roc_auc'] for f in filenames]
for k, v in results.items():
print('{}: {:.4f} +- {:.4f}'.format(k, np.mean(v), np.std(v)))
avg_results.append(np.mean(v))
std_results.append(np.std(v))
# compute the std of average results over multiple runs
min_runs = min([len(v) for v in results.values()])
std_rec = []
for i in range(min_runs):
ith_run = [
results[get_class_name_from_index(c, dataset_name)][i]
for c in range(n_classes)
]
std_rec.append(np.mean(ith_run))
print('-------------------------------------------')
print('Average: {:.4f} +- {:.4f}'.format(np.mean(avg_results),
np.std(std_rec)))
print('Formated:')
for r, s in zip(avg_results, std_results):
print('{:.4f}~{:.4f}'.format(r, s))
print('{:.4f}~{:.4f}'.format(np.mean(avg_results), np.std(std_rec)))
def _cae_pytorch_experiment(x_train, y_train, dataset_name, single_class_ind,
gpu_q, p):
gpu_to_use = gpu_q.get()
n_channels = x_train.shape[get_channels_axis()]
model = CAE_pytorch(in_channels=n_channels)
batch_size = 128
model = model.cuda()
trainset = trainset_pytorch(train_data=x_train,
train_labels=y_train,
transform=transform_train)
trainloader = data.DataLoader(trainset,
batch_size=batch_size,
shuffle=True)
cudnn.benchmark = True
criterion = nn.MSELoss()
# use adam always
optimizer = optim.Adam(model.parameters(), eps=1e-7, weight_decay=0.0005)
epochs = 250
# #########################Training########################
train_cae(trainloader, model, criterion, optimizer, epochs)
# #######################Testin############################
testloader = data.DataLoader(trainset, batch_size=1024, shuffle=False)
losses, reps = test_cae_pytorch(testloader, model)
losses = losses - losses.min()
losses = losses / (1e-8 + losses.max())
scores = 1 - losses
res_file_name = '{}_cae-{}_{}_{}.npz'.format(
dataset_name, p,
get_class_name_from_index(single_class_ind, dataset_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, y_train, res_file_path)
# Use reps to train iforest
clf = IsolationForest(contamination=p, n_jobs=4).fit(reps)
scores_iforest = clf.decision_function(reps)
iforest_file_name = '{}_cae-iforest-{}_{}_{}.npz'.format(
dataset_name, p,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
iforest_file_path = os.path.join(RESULTS_DIR, dataset_name,
iforest_file_name)
save_roc_pr_curve_data(scores_iforest, y_train, iforest_file_path)
gpu_q.put(gpu_to_use)
def _dsebm_experiment(dataset_load_fn, dataset_name, single_class_ind, gpu_q):
gpu_to_use = gpu_q.get()
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_to_use
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
n_channels = x_train.shape[get_channels_axis()]
input_side = x_train.shape[2] # image side will always be at shape[2]
encoder_mdl = conv_encoder(input_side, n_channels, representation_activation='relu')
energy_mdl = dsebm.create_energy_model(encoder_mdl)
reconstruction_mdl = dsebm.create_reconstruction_model(energy_mdl)
# optimization parameters
batch_size = 128
epochs = 200
reconstruction_mdl.compile('adam', 'mse')
x_train_task = x_train[y_train.flatten() == single_class_ind]
x_test_task = x_test[y_test.flatten() == single_class_ind] # This is just for visual monitoring
reconstruction_mdl.fit(x=x_train_task, y=x_train_task,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test_task, x_test_task))
scores = -energy_mdl.predict(x_test, batch_size)
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_dsebm_{}_{}.npz'.format(dataset_name,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
gpu_q.put(gpu_to_use)
def _raw_ocsvm_experiment(dataset_load_fn, dataset_name, single_class_ind):
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
x_train = x_train.reshape((len(x_train), -1))
x_test = x_test.reshape((len(x_test), -1))
x_train_task = x_train[y_train.flatten() == single_class_ind]
if dataset_name in ['cats-vs-dogs']: # OC-SVM is quadratic on the number of examples, so subsample training set
subsample_inds = np.random.choice(len(x_train_task), 5000, replace=False)
x_train_task = x_train_task[subsample_inds]
pg = ParameterGrid({'nu': np.linspace(0.1, 0.9, num=9),
'gamma': np.logspace(-7, 2, num=10, base=2)})
results = Parallel(n_jobs=6)(
delayed(_train_ocsvm_and_score)(d, x_train_task, y_test.flatten() == single_class_ind, x_test)
for d in pg)
best_params, best_auc_score = max(zip(pg, results), key=lambda t: t[-1])
best_ocsvm = OneClassSVM(**best_params).fit(x_train_task)
scores = best_ocsvm.decision_function(x_test)
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_raw-oc-svm_{}_{}.npz'.format(dataset_name,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
def _RDAE_experiment(x_train, y_train, dataset_name, single_class_ind, gpu_q,
p):
gpu_to_use = gpu_q.get()
cudnn.benchmark = True
n_channels = x_train.shape[get_channels_axis()]
model = CAE_pytorch(in_channels=n_channels)
model = model.cuda()
optimizer = optim.Adam(model.parameters(), eps=1e-7, weight_decay=0.0005)
criterion = nn.MSELoss()
epochs = 20
inner_epochs = 1
lmbda = 0.00065
# train RDAE
losses = train_robust_cae(x_train, model, criterion, optimizer, lmbda,
inner_epochs, epochs // inner_epochs, False)
losses = losses - losses.min()
losses = losses / (1e-8 + losses.max())
scores = 1 - losses
res_file_name = '{}_rdae-{}_{}_{}.npz'.format(
dataset_name, p,
get_class_name_from_index(single_class_ind, dataset_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, y_train, res_file_path)
gpu_q.put(gpu_to_use)
def _cae_ocsvm_experiment(dataset_load_fn, dataset_name, single_class_ind,
gpu_q):
gpu_to_use = gpu_q.get()
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_to_use
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
n_channels = x_train.shape[get_channels_axis()]
input_side = x_train.shape[2] # channel side will always be at shape[2]
enc = conv_encoder(input_side, n_channels)
dec = conv_decoder(input_side, n_channels)
x_in = Input(shape=x_train.shape[1:])
x_rec = dec(enc(x_in))
cae = Model(x_in, x_rec)
cae.compile('adam', 'mse')
x_train_task = x_train[y_train.flatten() == single_class_ind]
x_test_task = x_test[y_test.flatten(
) == single_class_ind] # This is just for visual monitoring
cae.fit(x=x_train_task,
y=x_train_task,
batch_size=128,
epochs=200,
validation_data=(x_test_task, x_test_task))
x_train_task_rep = enc.predict(x_train_task, batch_size=128)
if dataset_name in [
'cats-vs-dogs'
]: # OC-SVM is quadratic on the number of examples, so subsample training set
subsample_inds = np.random.choice(len(x_train_task_rep),
2500,
replace=False)
x_train_task_rep = x_train_task_rep[subsample_inds]
x_test_rep = enc.predict(x_test, batch_size=128)
pg = ParameterGrid({
'nu': np.linspace(0.1, 0.9, num=9),
'gamma': np.logspace(-7, 2, num=10, base=2)
})
results = Parallel(n_jobs=6)(delayed(_train_ocsvm_and_score)(
d, x_train_task_rep, y_test.flatten() == single_class_ind, x_test_rep)
for d in pg)
best_params, best_auc_score = max(zip(pg, results), key=lambda t: t[-1])
print(best_params)
best_ocsvm = OneClassSVM(**best_params).fit(x_train_task_rep)
scores = best_ocsvm.decision_function(x_test_rep)
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_cae-oc-svm_{}_{}.npz'.format(
dataset_name, get_class_name_from_index(single_class_ind,
dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
gpu_q.put(gpu_to_use)
def _adgan_experiment(dataset_load_fn, dataset_name, single_class_ind, gpu_q):
gpu_to_use = gpu_q.get()
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_to_use
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
if len(x_test) > 5000:
# subsample x_test due to runtime complexity
chosen_inds = np.random.choice(len(x_test), 5000, replace=False)
x_test = x_test[chosen_inds]
y_test = y_test[chosen_inds]
n_channels = x_train.shape[get_channels_axis()]
input_side = x_train.shape[2] # image side will always be at shape[2]
critic = conv_encoder(input_side,
n_channels,
representation_dim=1,
representation_activation='linear')
noise_size = 256
generator = conv_decoder(input_side,
n_channels=n_channels,
representation_dim=noise_size)
def prior_gen(b_size):
return np.random.normal(size=(b_size, noise_size))
batch_size = 128
epochs = 100
x_train_task = x_train[y_train.flatten() == single_class_ind]
def data_gen(b_size):
chosen_inds = np.random.choice(len(x_train_task),
b_size,
replace=False)
return x_train_task[chosen_inds]
adgan.train_wgan_with_grad_penalty(prior_gen,
generator,
data_gen,
critic,
batch_size,
epochs,
grad_pen_coef=20)
scores = adgan.scores_from_adgan_generator(x_test, prior_gen, generator)
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_adgan_{}_{}.npz'.format(
dataset_name, get_class_name_from_index(single_class_ind,
dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
gpu_q.put(gpu_to_use)
def _dagmm_experiment(dataset_load_fn, dataset_name, single_class_ind, gpu_q):
gpu_to_use = gpu_q.get()
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_to_use
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
n_channels = x_train.shape[get_channels_axis()]
input_side = x_train.shape[2] # image side will always be at shape[2]
enc = conv_encoder(input_side, n_channels, representation_dim=5,
representation_activation='linear')
dec = conv_decoder(input_side, n_channels=n_channels, representation_dim=enc.output_shape[-1])
n_components = 3
estimation = Sequential([Dense(64, activation='tanh', input_dim=enc.output_shape[-1] + 2), Dropout(0.5),
Dense(10, activation='tanh'), Dropout(0.5),
Dense(n_components, activation='softmax')]
)
batch_size = 256
epochs = 200
lambda_diag = 0.0005
lambda_energy = 0.01
dagmm_mdl = dagmm.create_dagmm_model(enc, dec, estimation, lambda_diag)
dagmm_mdl.compile('adam', ['mse', lambda y_true, y_pred: lambda_energy*y_pred])
x_train_task = x_train[y_train.flatten() == single_class_ind]
x_test_task = x_test[y_test.flatten() == single_class_ind] # This is just for visual monitoring
dagmm_mdl.fit(x=x_train_task, y=[x_train_task, np.zeros((len(x_train_task), 1))], # second y is dummy
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test_task, [x_test_task, np.zeros((len(x_test_task), 1))]),
# verbose=0
)
energy_mdl = Model(dagmm_mdl.input, dagmm_mdl.output[-1])
scores = -energy_mdl.predict(x_test, batch_size)
scores = scores.flatten()
if not np.all(np.isfinite(scores)):
min_finite = np.min(scores[np.isfinite(scores)])
scores[~np.isfinite(scores)] = min_finite - 1
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_dagmm_{}_{}.npz'.format(dataset_name,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
gpu_q.put(gpu_to_use)
def _transformations_experiment(dataset_load_fn, dataset_name, single_class_ind, gpu_q):
gpu_to_use = gpu_q.get()
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_to_use
(x_train, y_train), (x_test, y_test) = dataset_load_fn()
if dataset_name in ['cats-vs-dogs']:
transformer = Transformer(16, 16)
n, k = (16, 8)
else:
transformer = Transformer(8, 8)
n, k = (10, 4)
mdl = create_wide_residual_network(x_train.shape[1:], transformer.n_transforms, n, k)
mdl.compile('adam',
'categorical_crossentropy',
['acc'])
x_train_task = x_train[y_train.flatten() == single_class_ind]
transformations_inds = np.tile(np.arange(transformer.n_transforms), len(x_train_task))
x_train_task_transformed = transformer.transform_batch(np.repeat(x_train_task, transformer.n_transforms, axis=0),
transformations_inds)
batch_size = 128
mdl.fit(x=x_train_task_transformed, y=to_categorical(transformations_inds),
batch_size=batch_size, epochs=int(np.ceil(200/transformer.n_transforms))
)
#################################################################################################
# simplified normality score
#################################################################################################
# preds = np.zeros((len(x_test), transformer.n_transforms))
# for t in range(transformer.n_transforms):
# preds[:, t] = mdl.predict(transformer.transform_batch(x_test, [t] * len(x_test)),
# batch_size=batch_size)[:, t]
#
# labels = y_test.flatten() == single_class_ind
# scores = preds.mean(axis=-1)
#################################################################################################
def calc_approx_alpha_sum(observations):
N = len(observations)
f = np.mean(observations, axis=0)
return (N * (len(f) - 1) * (-psi(1))) / (
N * np.sum(f * np.log(f)) - np.sum(f * np.sum(np.log(observations), axis=0)))
def inv_psi(y, iters=5):
# initial estimate
cond = y >= -2.22
x = cond * (np.exp(y) + 0.5) + (1 - cond) * -1 / (y - psi(1))
for _ in range(iters):
x = x - (psi(x) - y) / polygamma(1, x)
return x
def fixed_point_dirichlet_mle(alpha_init, log_p_hat, max_iter=1000):
alpha_new = alpha_old = alpha_init
for _ in range(max_iter):
alpha_new = inv_psi(psi(np.sum(alpha_old)) + log_p_hat)
if np.sqrt(np.sum((alpha_old - alpha_new) ** 2)) < 1e-9:
break
alpha_old = alpha_new
return alpha_new
def dirichlet_normality_score(alpha, p):
return np.sum((alpha - 1) * np.log(p), axis=-1)
scores = np.zeros((len(x_test),))
observed_data = x_train_task
for t_ind in range(transformer.n_transforms):
observed_dirichlet = mdl.predict(transformer.transform_batch(observed_data, [t_ind] * len(observed_data)),
batch_size=1024)
log_p_hat_train = np.log(observed_dirichlet).mean(axis=0)
alpha_sum_approx = calc_approx_alpha_sum(observed_dirichlet)
alpha_0 = observed_dirichlet.mean(axis=0) * alpha_sum_approx
mle_alpha_t = fixed_point_dirichlet_mle(alpha_0, log_p_hat_train)
x_test_p = mdl.predict(transformer.transform_batch(x_test, [t_ind] * len(x_test)),
batch_size=1024)
scores += dirichlet_normality_score(mle_alpha_t, x_test_p)
scores /= transformer.n_transforms
labels = y_test.flatten() == single_class_ind
res_file_name = '{}_transformations_{}_{}.npz'.format(dataset_name,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
res_file_path = os.path.join(RESULTS_DIR, dataset_name, res_file_name)
save_roc_pr_curve_data(scores, labels, res_file_path)
mdl_weights_name = '{}_transformations_{}_{}_weights.h5'.format(dataset_name,
get_class_name_from_index(single_class_ind, dataset_name),
datetime.now().strftime('%Y-%m-%d-%H%M'))
mdl_weights_path = os.path.join(RESULTS_DIR, dataset_name, mdl_weights_name)
mdl.save_weights(mdl_weights_path)
gpu_q.put(gpu_to_use)
def _E3Outlier_experiment(x_train, y_train, dataset_name, single_class_ind,
gpu_q, p):
"""Surrogate Supervision Discriminative Network training."""
gpu_to_use = gpu_q.get()
n_channels = x_train.shape[get_channels_axis()]
if OP_TYPE == 'RA':
transformer = RA(8, 8)
elif OP_TYPE == 'RA+IA':
transformer = RA_IA(8, 8, 12)
elif OP_TYPE == 'RA+IA+PR':
transformer = RA_IA_PR(8, 8, 12, 23, 2)
else:
raise NotImplementedError
print(transformer.n_transforms)
if BACKEND == 'wrn':
n, k = (10, 4)
model = WideResNet(num_classes=transformer.n_transforms,
depth=n,
widen_factor=k,
in_channel=n_channels)
elif BACKEND == 'resnet20':
n = 20
model = ResNet(num_classes=transformer.n_transforms,
depth=n,
in_channels=n_channels)
elif BACKEND == 'resnet50':
n = 50
model = ResNet(num_classes=transformer.n_transforms,
depth=n,
in_channels=n_channels)
elif BACKEND == 'densenet22':
n = 22
model = DenseNet(num_classes=transformer.n_transforms,
depth=n,
in_channels=n_channels)
elif BACKEND == 'densenet40':
n = 40
model = DenseNet(num_classes=transformer.n_transforms,
depth=n,
in_channels=n_channels)
else:
raise NotImplementedError('Unimplemented backend: {}'.format(BACKEND))
print('Using backend: {} ({})'.format(type(model).__name__, BACKEND))
x_train_task = x_train
transformations_inds = np.tile(np.arange(transformer.n_transforms),
len(x_train_task))
x_train_task_transformed = transformer.transform_batch(
np.repeat(x_train_task, transformer.n_transforms, axis=0),
transformations_inds)
# parameters for training
trainset = trainset_pytorch(train_data=x_train_task_transformed,
train_labels=transformations_inds,
transform=transform_train)
batch_size = 128
trainloader = data.DataLoader(trainset,
batch_size=batch_size,
shuffle=True)
cudnn.benchmark = True
criterion = nn.CrossEntropyLoss()
model = torch.nn.DataParallel(model).cuda()
if dataset_name in ['mnist', 'fashion-mnist']:
optimizer = optim.SGD(model.parameters(),
lr=0.001,
momentum=0.9,
weight_decay=0.0005)
else:
optimizer = optim.Adam(model.parameters(),
eps=1e-7,
weight_decay=0.0005)
epochs = int(np.ceil(250 / transformer.n_transforms))
train_pytorch(trainloader, model, criterion, optimizer, epochs)
# SSD-IF
test_set = testset_pytorch(test_data=x_train_task,
transform=transform_test)
x_train_task_rep = get_features_pytorch(testloader=data.DataLoader(
test_set, batch_size=batch_size, shuffle=False),
model=model).numpy()
clf = IsolationForest(contamination=p, n_jobs=4).fit(x_train_task_rep)
if_scores = clf.decision_function(x_train_task_rep)
res_file_name = '{}_ssd-iforest-{}_{}_{}.npz'.format(
dataset_name, p,
get_class_name_from_index(single_class_ind, dataset_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(if_scores, y_train, res_file_path)
# E3Outlier
if SCORE_MODE == 'pl_mean':
preds = np.zeros((len(x_train_task), transformer.n_transforms))
original_preds = np.zeros((transformer.n_transforms, len(x_train_task),
transformer.n_transforms))
for t in range(transformer.n_transforms):
idx = np.squeeze(
np.array([range(x_train_task.shape[0])]) *
transformer.n_transforms + t)
test_set = testset_pytorch(
test_data=x_train_task_transformed[idx, :],
transform=transform_test)
original_preds[t, :, :] = softmax(
test_pytorch(testloader=data.DataLoader(test_set,
batch_size=batch_size,
shuffle=False),
model=model))
preds[:, t] = original_preds[t, :, :][:, t]
scores = preds.mean(axis=-1)
elif SCORE_MODE == 'max_mean':
preds = np.zeros((len(x_train_task), transformer.n_transforms))
original_preds = np.zeros((transformer.n_transforms, len(x_train_task),
transformer.n_transforms))
for t in range(transformer.n_transforms):
idx = np.squeeze(
np.array([range(x_train_task.shape[0])]) *
transformer.n_transforms + t)
test_set = testset_pytorch(
test_data=x_train_task_transformed[idx, :],
transform=transform_test)
original_preds[t, :, :] = softmax(
test_pytorch(testloader=data.DataLoader(test_set,
batch_size=batch_size,
shuffle=False),
model=model))
preds[:, t] = np.max(original_preds[t, :, :], axis=1)
scores = preds.mean(axis=-1)
elif SCORE_MODE == 'neg_entropy':
preds = np.zeros((len(x_train_task), transformer.n_transforms))
original_preds = np.zeros((transformer.n_transforms, len(x_train_task),
transformer.n_transforms))
for t in range(transformer.n_transforms):
idx = np.squeeze(
np.array([range(x_train_task.shape[0])]) *
transformer.n_transforms + t)
test_set = testset_pytorch(
test_data=x_train_task_transformed[idx, :],
transform=transform_test)
original_preds[t, :, :] = softmax(
test_pytorch(testloader=data.DataLoader(test_set,
batch_size=batch_size,
shuffle=False),
model=model))
for s in range(len(x_train_task)):
preds[s, t] = neg_entropy(original_preds[t, s, :])
scores = preds.mean(axis=-1)
else:
raise NotImplementedError
res_file_name = '{}_e3outlier-{}_{}_{}.npz'.format(
dataset_name, p,
get_class_name_from_index(single_class_ind, dataset_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, y_train, res_file_path)
gpu_q.put(gpu_to_use)
