fedex/mt
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

black formatted files before changes

Browse Source
This commit is contained in:
Jan Kowalczyk
2024-06-28 11:36:46 +02:00
parent d33c6b1e16
commit 71f9662022
40 changed files with 2938 additions and 1260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
Deep-SAD-PyTorch/src/optim/DeepSAD_trainer.py
View File

@@ -13,11 +13,29 @@ import numpy as np
class DeepSADTrainer(BaseTrainer):
def __init__(self, c, eta: float, optimizer_name: str = 'adam', lr: float = 0.001, n_epochs: int = 150,
lr_milestones: tuple = (), batch_size: int = 128, weight_decay: float = 1e-6, device: str = 'cuda',
n_jobs_dataloader: int = 0):
super().__init__(optimizer_name, lr, n_epochs, lr_milestones, batch_size, weight_decay, device,
n_jobs_dataloader)
def __init__(
self,
c,
eta: float,
optimizer_name: str = "adam",
lr: float = 0.001,
n_epochs: int = 150,
lr_milestones: tuple = (),
batch_size: int = 128,
weight_decay: float = 1e-6,
device: str = "cuda",
n_jobs_dataloader: int = 0,
):
super().__init__(
optimizer_name,
lr,
n_epochs,
lr_milestones,
batch_size,
weight_decay,
device,
n_jobs_dataloader,
)
# Deep SAD parameters
self.c = torch.tensor(c, device=self.device) if c is not None else None
@@ -36,39 +54,50 @@ class DeepSADTrainer(BaseTrainer):
logger = logging.getLogger()
# Get train data loader
train_loader, _ = dataset.loaders(batch_size=self.batch_size, num_workers=self.n_jobs_dataloader)
train_loader, _ = dataset.loaders(
batch_size=self.batch_size, num_workers=self.n_jobs_dataloader
)
# Set device for network
net = net.to(self.device)
# Set optimizer (Adam optimizer for now)
optimizer = optim.Adam(net.parameters(), lr=self.lr, weight_decay=self.weight_decay)
optimizer = optim.Adam(
net.parameters(), lr=self.lr, weight_decay=self.weight_decay
)
# Set learning rate scheduler
scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=self.lr_milestones, gamma=0.1)
scheduler = optim.lr_scheduler.MultiStepLR(
optimizer, milestones=self.lr_milestones, gamma=0.1
)
# Initialize hypersphere center c (if c not loaded)
if self.c is None:
logger.info('Initializing center c...')
logger.info("Initializing center c...")
self.c = self.init_center_c(train_loader, net)
logger.info('Center c initialized.')
logger.info("Center c initialized.")
# Training
logger.info('Starting training...')
logger.info("Starting training...")
start_time = time.time()
net.train()
for epoch in range(self.n_epochs):
scheduler.step()
if epoch in self.lr_milestones:
logger.info(' LR scheduler: new learning rate is %g' % float(scheduler.get_lr()[0]))
logger.info(
" LR scheduler: new learning rate is %g"
% float(scheduler.get_lr()[0])
)
epoch_loss = 0.0
n_batches = 0
epoch_start_time = time.time()
for data in train_loader:
inputs, _, semi_targets, _ = data
inputs, semi_targets = inputs.to(self.device), semi_targets.to(self.device)
inputs, semi_targets = inputs.to(self.device), semi_targets.to(
self.device
)
# Zero the network parameter gradients
optimizer.zero_grad()
@@ -76,7 +105,11 @@ class DeepSADTrainer(BaseTrainer):
# Update network parameters via backpropagation: forward + backward + optimize
outputs = net(inputs)
dist = torch.sum((outputs - self.c) ** 2, dim=1)
losses = torch.where(semi_targets == 0, dist, self.eta * ((dist + self.eps) ** semi_targets.float()))
losses = torch.where(
semi_targets == 0,
dist,
self.eta * ((dist + self.eps) ** semi_targets.float()),
)
loss = torch.mean(losses)
loss.backward()
optimizer.step()
@@ -86,12 +119,14 @@ class DeepSADTrainer(BaseTrainer):
# log epoch statistics
epoch_train_time = time.time() - epoch_start_time
logger.info(f'| Epoch: {epoch + 1:03}/{self.n_epochs:03} | Train Time: {epoch_train_time:.3f}s '
f'| Train Loss: {epoch_loss / n_batches:.6f} |')
logger.info(
f"| Epoch: {epoch + 1:03}/{self.n_epochs:03} | Train Time: {epoch_train_time:.3f}s "
f"| Train Loss: {epoch_loss / n_batches:.6f} |"
)
self.train_time = time.time() - start_time
logger.info('Training Time: {:.3f}s'.format(self.train_time))
logger.info('Finished training.')
logger.info("Training Time: {:.3f}s".format(self.train_time))
logger.info("Finished training.")
return net
@@ -99,13 +134,15 @@ class DeepSADTrainer(BaseTrainer):
logger = logging.getLogger()
# Get test data loader
_, test_loader = dataset.loaders(batch_size=self.batch_size, num_workers=self.n_jobs_dataloader)
_, test_loader = dataset.loaders(
batch_size=self.batch_size, num_workers=self.n_jobs_dataloader
)
# Set device for network
net = net.to(self.device)
# Testing
logger.info('Starting testing...')
logger.info("Starting testing...")
epoch_loss = 0.0
n_batches = 0
start_time = time.time()
@@ -122,14 +159,22 @@ class DeepSADTrainer(BaseTrainer):
outputs = net(inputs)
dist = torch.sum((outputs - self.c) ** 2, dim=1)
losses = torch.where(semi_targets == 0, dist, self.eta * ((dist + self.eps) ** semi_targets.float()))
losses = torch.where(
semi_targets == 0,
dist,
self.eta * ((dist + self.eps) ** semi_targets.float()),
)
loss = torch.mean(losses)
scores = dist
# Save triples of (idx, label, score) in a list
idx_label_score += list(zip(idx.cpu().data.numpy().tolist(),
labels.cpu().data.numpy().tolist(),
scores.cpu().data.numpy().tolist()))
idx_label_score += list(
zip(
idx.cpu().data.numpy().tolist(),
labels.cpu().data.numpy().tolist(),
scores.cpu().data.numpy().tolist(),
)
)
epoch_loss += loss.item()
n_batches += 1
@@ -144,10 +189,10 @@ class DeepSADTrainer(BaseTrainer):
self.test_auc = roc_auc_score(labels, scores)
# Log results
logger.info('Test Loss: {:.6f}'.format(epoch_loss / n_batches))
logger.info('Test AUC: {:.2f}%'.format(100. * self.test_auc))
logger.info('Test Time: {:.3f}s'.format(self.test_time))
logger.info('Finished testing.')
logger.info("Test Loss: {:.6f}".format(epoch_loss / n_batches))
logger.info("Test AUC: {:.2f}%".format(100.0 * self.test_auc))
logger.info("Test Time: {:.3f}s".format(self.test_time))
logger.info("Finished testing.")
def init_center_c(self, train_loader: DataLoader, net: BaseNet, eps=0.1):
"""Initialize hypersphere center c as the mean from an initial forward pass on the data."""