def train_robust_cae(x_train, model, criterion, optimizer, lmbda, inner_epochs, outer_epochs, reinit=True):
batch_size = 128
S = np.zeros_like(x_train) # reside on numpy as x_train
def get_reconstruction(loader):
model.eval()
rc = []
for batch, _ in loader:
with torch.no_grad():
rc.append(model(batch.cuda()).cpu().numpy())
out = np.concatenate(rc, axis=0)
# NOTE: transform_train swaps the channel axis, swap back to yield the same shape
out = out.transpose((0, 2, 3, 1))
return out
for oe in range(outer_epochs):
# update AE
if reinit:
# Since our CAE_pytorch does not implement reset_parameters, regenerate a new model if reinit.
del model
model = CAE_pytorch(in_channels=x_train.shape[get_channels_axis()]).cuda()
model.train()
trainset = trainset_pytorch(x_train-S, train_labels=np.ones((x_train.shape[0], )), transform=transform_train)
trainloader = data.DataLoader(trainset, batch_size=batch_size, shuffle=True)
for ie in range(inner_epochs):
for batch_idx, (inputs, _) in enumerate(trainloader):
inputs = inputs.cuda()
outputs = model(inputs)
loss = criterion(inputs, outputs)
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (batch_idx + 1) % 10 == 0:
print('Epoch: [{} | {} ({} | {})], batch: {}, loss: {}'.format(
ie+1, inner_epochs, oe+1, outer_epochs, batch_idx+1, loss.item())
)
# update S via l21 proximal operator
testloader = data.DataLoader(trainset, batch_size=1024, shuffle=False)
recon = get_reconstruction(testloader)
S = prox_l21(x_train - recon, lmbda)
# get final reconstruction
finalset = trainset_pytorch(x_train - S, train_labels=np.ones((x_train.shape[0],)), transform=transform_train)
finalloader = data.DataLoader(finalset, batch_size=1024, shuffle=False)
reconstruction = get_reconstruction(finalloader)
losses = ((x_train-S-reconstruction) ** 2).sum(axis=(1, 2, 3), keepdims=False)
return losses
def _DRAE_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 = DRAELossAutograd(lamb=0.1)
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 = '{}_drae-{}_{}_{}.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 _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)