timesead.models.other.thoc

Classes

THOC

Base class for all neural network modules.

THOCLoss

Base class for all neural network modules.

THOCTrainer

THOCAnomalyDetector

Base class for all neural network modules.

Module Contents

class timesead.models.other.thoc.THOC(input_size, hidden_sizes: Sequence[int] | int = 128, n_hidden_layers: int | None = 3, dilations: Sequence[int] | int = [1, 2, 4], clusters_dims: Sequence[int] | int = 6, tau: float = 100.0)

Bases: timesead.models.BaseModel

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

  • hidden_sizes (Union[Sequence[int], int])

  • n_hidden_layers (Optional[int])

  • dilations (Union[Sequence[int], int])

  • clusters_dims (Union[Sequence[int], int])

  • tau (float)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

dilations = [1, 2, 4]
clusters_dims = 6
tau = 100.0
drnn
centers
transforms
out_project
join_f
grouped_parameters() → Tuple[Iterator[torch.nn.Parameter], Ellipsis]
Return type:

Tuple[Iterator[torch.nn.Parameter], Ellipsis]

knn_init_centers(dl: torch.utils.data.DataLoader, num_batches: int)
Function that initiates the centers by Kmeans on the training set. Since taking the whole training data is to large, we only

consider the first (shuffled) num_batches batches.

dl (torch.utils.data.DataLoader): Dataloader from which we take the first num_batches batches.

Ideally the dataloader should shuffle the batches.

num_batches (int, optional): Number of batches to use for inititalization. If num_batches = 0 the

centers will not be initialized by Kmeans at all. Default is 20.

Parameters:
forward(x: torch.Tensor) → torch.Tensor
Parameters:

x (torch.Tensor)

Return type:

torch.Tensor

class timesead.models.other.thoc.THOCLoss(model: THOC, lambda_orth: float = 1.0, lambda_tss: float = 10.0)

Bases: timesead.optim.loss.Loss

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

Initialize internal Module state, shared by both nn.Module and ScriptModule.

model
lambda_orth = 1.0
lambda_tss = 10.0
thoc_loss(f_final: torch.Tensor, R_last: torch.Tensor) → torch.Tensor
Parameters:
Return type:

torch.Tensor

orth_loss()
tss_loss(drnn_outs: List[torch.Tensor], target: torch.Tensor) → torch.Tensor

Calclulates the time-series prediction error. (Equation 12)

inputs:

drnn_outs (torch.Tensor) x (torch.Tensor)

Parameters:
Return type:

torch.Tensor

forward(predictions: Tuple[torch.Tensor, Ellipsis], targets: Tuple[torch.Tensor, Ellipsis] = None, *args, **kwargs) → torch.Tensor
Parameters:
Return type:

torch.Tensor

class timesead.models.other.thoc.THOCTrainer(*args, tau_decrease_steps: int = 5, tau_decrease_gamma: float = 2.0 / 3.0, init_centers_batches: int = 20, **kwargs)

Bases: timesead.optim.trainer.Trainer

Parameters:

  • tau_decrease_steps (int)

  • tau_decrease_gamma (float)

  • init_centers_batches (int)

tau_decrease_steps = 5
tau_decrease_gamma = 0.6666666666666666
init_centers_batches = 20
validate_batch(network: torch.nn.Module, val_metrics: Dict[str, Callable], b_inputs: Tuple[torch.Tensor, Ellipsis], b_targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) → Dict[str, float]
Parameters:
Return type:

Dict[str, float]

train_batch(network: THOC, losses: List[timesead.optim.loss.Loss], optimizers: List[torch.optim.Optimizer], epoch: int, num_epochs: int, b_inputs: Tuple[torch.Tensor, Ellipsis], b_targets: Tuple[torch.Tensor, Ellipsis]) → List[float]
Parameters:
Return type:

List[float]

train(network: THOC, *args, **kwargs)
Parameters:

network (THOC)

class timesead.models.other.thoc.THOCAnomalyDetector(model: THOC)

Bases: timesead.models.common.AnomalyDetector

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

model (THOC)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

model
compute_online_anomaly_score(inputs: Tuple[torch.Tensor, Ellipsis]) → torch.Tensor

Compute the online anomaly score for a batch of inputs. The output tensor must have the same shape as the output of format_targets when called with the corresponding targets for this batch. This method expects a window (or a batch of windows) as its input and should return a score for the last point in the window.

Parameters:

inputs (Tuple[torch.Tensor, Ellipsis]) – tuple of input tensors

Returns:

Tensor of shape (B,) that contains the anomaly scores for this batch

Return type:

torch.Tensor

abstract compute_offline_anomaly_score(inputs: Tuple[torch.Tensor, Ellipsis]) → torch.Tensor

Compute the offline anomaly score for a batch of inputs. The output tensor must have the same shape as the output of format_targets when called with the corresponding targets for this batch. This method expects a window (or a batch of windows) as its input and should return a score for the last point in the window.

Parameters:

inputs (Tuple[torch.Tensor, Ellipsis]) – tuple of input tensors

Returns:

Tensor of shape (N,) that contains the anomaly scores for this batch

Return type:

torch.Tensor

fit(dataset: torch.utils.data.DataLoader) → None

Fit this anomaly detector on a dataset. Note that we assume only normal data here.

Parameters:

dataset (torch.utils.data.DataLoader) – A dataset

Return type:

None

format_online_targets(targets: Tuple[torch.Tensor, Ellipsis]) → torch.Tensor

Format the labels for a batch of targets. The output tensor must have the same shape as the output of compute_online_anomaly_score when called with the corresponding inputs for this batch.

Parameters:

targets (Tuple[torch.Tensor, Ellipsis]) – tuple of target tensors

Returns:

Tensor of shape (B,) that contains the ground truth labels for this batch

Return type:

torch.Tensor