alibi_detect.utils.pytorch package

class alibi_detect.utils.pytorch.DeepKernel(proj, kernel_a='rbf', kernel_b='rbf', eps='trainable')

Bases: Module

Computes similarities as k(x,y) = (1-eps)*k_a(proj(x), proj(y)) + eps*k_b(x,y). A forward pass takes a batch of instances x [Nx, features] and y [Ny, features] and returns the kernel matrix [Nx, Ny].

Parameters:

• proj (Module) – The projection to be applied to the inputs before applying kernel_a

• kernel_a (Union[Module, str]) – The kernel to apply to the projected inputs. Defaults to a Gaussian RBF with trainable bandwidth.

• kernel_b (Union[Module, str, None]) – The kernel to apply to the raw inputs. Defaults to a Gaussian RBF with trainable bandwidth. Set to None in order to use only the deep component (i.e. eps=0).

• eps (Union[float, str]) – The proportion (in [0,1]) of weight to assign to the kernel applied to raw inputs. This can be either specified or set to ‘trainable’. Only relavent if kernel_b is not None.

property eps: torch.Tensor

Return type:

Tensor

forward(x, y)

Return type:

Tensor

classmethod from_config(config)

get_config()

Return type:

dict

class alibi_detect.utils.pytorch.GaussianRBF(sigma=None, init_sigma_fn=None, trainable=False)

Bases: Module

__init__(sigma=None, init_sigma_fn=None, trainable=False)

Gaussian RBF kernel: k(x,y) = exp(-(1/(2*sigma^2)||x-y||^2). A forward pass takes a batch of instances x [Nx, features] and y [Ny, features] and returns the kernel matrix [Nx, Ny].

Parameters:

• sigma (Optional[Tensor]) – Bandwidth used for the kernel. Needn’t be specified if being inferred or trained. Can pass multiple values to eval kernel with and then average.

• init_sigma_fn (Optional[Callable]) – Function used to compute the bandwidth sigma. Used when sigma is to be inferred. The function’s signature should match sigma_median(), meaning that it should take in the tensors x, y and dist and return sigma. If None, it is set to sigma_median().

• trainable (bool) – Whether or not to track gradients w.r.t. sigma to allow it to be trained.

forward(x, y, infer_sigma=False)

Return type:

Tensor

classmethod from_config(config)

Instantiates a kernel from a config dictionary.

Parameters:

config – A kernel config dictionary.

get_config()

Returns a serializable config dict (excluding the input_sigma_fn, which is serialized in alibi_detect.saving).

Return type:

dict

property sigma: torch.Tensor

Return type:

Tensor

class alibi_detect.utils.pytorch.TorchDataset(*indexables)

Bases: Dataset

alibi_detect.utils.pytorch.batch_compute_kernel_matrix(x, y, kernel, device=None, batch_size=10000000000, preprocess_fn=None)

Compute the kernel matrix between x and y by filling in blocks of size batch_size x batch_size at a time.

Parameters:

• x (Union[list, ndarray, Tensor]) – Reference set.

• y (Union[list, ndarray, Tensor]) – Test set.

• kernel (Union[Module, Sequential]) – PyTorch module.

• device (Optional[device]) – Device type used. The default None tries to use the GPU and falls back on CPU if needed. Can be specified by passing either torch.device(‘cuda’) or torch.device(‘cpu’).

• batch_size (int) – Batch size used during prediction.

• preprocess_fn (Optional[Callable[..., Tensor]]) – Optional preprocessing function for each batch.

Return type:

Tensor

Returns:

Kernel matrix in the form of a torch tensor

alibi_detect.utils.pytorch.get_device(device=None)

Instantiates a PyTorch device object.

Parameters:

device (Union[Literal[‘cuda’, ‘gpu’, ‘cpu’], device, None]) – Either None, a str (‘gpu’, ‘cuda’ or ‘cpu’) indicating the device to choose, or an already instantiated device object. If None, the GPU is selected if it is detected, otherwise the CPU is used as a fallback.

Return type:

device

Returns:

The instantiated device object.

alibi_detect.utils.pytorch.mmd2(x, y, kernel)

Compute MMD^2 between 2 samples.

Parameters:

• x (Tensor) – Batch of instances of shape [Nx, features].

• y (Tensor) – Batch of instances of shape [Ny, features].

• kernel (Callable) – Kernel function.

Return type:

float

Returns:

MMD^2 between the samples x and y.

alibi_detect.utils.pytorch.mmd2_from_kernel_matrix(kernel_mat, m, permute=False, zero_diag=True)

Compute maximum mean discrepancy (MMD^2) between 2 samples x and y from the full kernel matrix between the samples.

Parameters:

• kernel_mat (Tensor) – Kernel matrix between samples x and y.

• m (int) – Number of instances in y.

• permute (bool) – Whether to permute the row indices. Used for permutation tests.

• zero_diag (bool) – Whether to zero out the diagonal of the kernel matrix.

Return type:

Tensor

Returns:

MMD^2 between the samples from the kernel matrix.

alibi_detect.utils.pytorch.permed_lsdds(k_all_c, x_perms, y_perms, H, H_lam_inv=None, lam_rd_max=0.2, return_unpermed=False)

Compute LSDD estimates from kernel matrix across various ref and test window samples

Parameters:

• k_all_c (Tensor) – Kernel matrix of similarities between all samples and the kernel centers.

• x_perms (List[Tensor]) – List of B reference window index vectors

• y_perms (List[Tensor]) – List of B test window index vectors

• H (Tensor) – Special (scaled) kernel matrix of similarities between kernel centers

• H_lam_inv (Optional[Tensor]) – Function of H corresponding to a particular regulariation parameter lambda. See Eqn 11 of Bu et al. (2017)

• lam_rd_max (float) – The maximum relative difference between two estimates of LSDD that the regularization parameter lambda is allowed to cause. Defaults to 0.2. Only relavent if H_lam_inv is not supplied.

• return_unpermed (bool) – Whether or not to return value corresponding to unpermed order defined by k_all_c

Return type:

Union[Tuple[Tensor, Tensor], Tuple[Tensor, Tensor, Tensor]]

Returns:

Vector of B LSDD estimates for each permutation, H_lam_inv which may have been inferred, and optionally the unpermed LSDD estimate.

alibi_detect.utils.pytorch.predict_batch(x, model, device=None, batch_size=10000000000, preprocess_fn=None, dtype=<class 'numpy.float32'>)

Make batch predictions on a model.

Parameters:

• x (Union[list, ndarray, Tensor]) – Batch of instances.

• model (Union[Callable, Module, Sequential]) – PyTorch model.

• device (Union[Literal[‘cuda’, ‘gpu’, ‘cpu’], device, None]) – Device type used. The default tries to use the GPU and falls back on CPU if needed. Can be specified by passing either 'cuda', 'gpu', 'cpu' or an instance of torch.device.

• batch_size (int) – Batch size used during prediction.

• preprocess_fn (Optional[Callable]) – Optional preprocessing function for each batch.

• dtype (Union[Type[generic], dtype]) – Model output type, e.g. np.float32 or torch.float32.

Return type:

Union[ndarray, Tensor, tuple]

Returns:

Numpy array, torch tensor or tuples of those with model outputs.

alibi_detect.utils.pytorch.predict_batch_transformer(x, model, tokenizer, max_len, device=None, batch_size=10000000000, dtype=<class 'numpy.float32'>)

Make batch predictions using a transformers tokenizer and model.

Parameters:

• x (Union[list, ndarray]) – Batch of instances.

• model (Union[Module, Sequential]) – PyTorch model.

• tokenizer (Callable) – Tokenizer for model.

• max_len (int) – Max sequence length for tokens.

• device (Union[Literal[‘cuda’, ‘gpu’, ‘cpu’], device, None]) – Device type used. The default tries to use the GPU and falls back on CPU if needed. Can be specified by passing either 'cuda', 'gpu', 'cpu' or an instance of torch.device.

• batch_size (int) – Batch size used during prediction.

• dtype (Union[Type[generic], dtype]) – Model output type, e.g. np.float32 or torch.float32.

Return type:

Union[ndarray, Tensor, tuple]

Returns:

Numpy array or torch tensor with model outputs.

alibi_detect.utils.pytorch.quantile(sample, p, type=7, sorted=False)

Estimate a desired quantile of a univariate distribution from a vector of samples

Parameters:

• sample (Tensor) – A 1D vector of values

• p (float) – The desired quantile in (0,1)

• type (int) – The method for computing the quantile. See https://wikipedia.org/wiki/Quantile#Estimating_quantiles_from_a_sample

• sorted (bool) – Whether or not the vector is already sorted into ascending order

Return type:

float

Returns:

An estimate of the quantile

alibi_detect.utils.pytorch.squared_pairwise_distance(x, y, a_min=1e-30)

PyTorch pairwise squared Euclidean distance between samples x and y.

Parameters:

• x (Tensor) – Batch of instances of shape [Nx, features].

• y (Tensor) – Batch of instances of shape [Ny, features].

• a_min (float) – Lower bound to clip distance values.

Return type:

Tensor

Returns:

Pairwise squared Euclidean distance [Nx, Ny].

alibi_detect.utils.pytorch.zero_diag(mat)

Set the diagonal of a matrix to 0

Parameters:

mat (Tensor) – A 2D square matrix

Return type:

Tensor

Returns:

A 2D square matrix with zeros along the diagonal

Submodules

• alibi_detect.utils.pytorch.data module
  • TorchDataset
• alibi_detect.utils.pytorch.distance module
  • batch_compute_kernel_matrix()
  • mmd2()
  • mmd2_from_kernel_matrix()
  • permed_lsdds()
  • squared_pairwise_distance()
• alibi_detect.utils.pytorch.kernels module
  • DeepKernel
    • DeepKernel.eps
    • DeepKernel.forward()
    • DeepKernel.from_config()
    • DeepKernel.get_config()
  • GaussianRBF
    • GaussianRBF.__init__()
    • GaussianRBF.forward()
    • GaussianRBF.from_config()
    • GaussianRBF.get_config()
    • GaussianRBF.sigma
  • sigma_median()
• alibi_detect.utils.pytorch.losses module
  • hinge_loss()
• alibi_detect.utils.pytorch.misc module
  • get_device()
  • get_optimizer()
  • quantile()
  • zero_diag()
• alibi_detect.utils.pytorch.prediction module
  • predict_batch()
  • predict_batch_transformer()