niteshade.models.BaseModel

class niteshade.models.BaseModel(architecture: list, optimizer: str, loss_func: str, lr: float, optim_kwargs={}, loss_kwargs={}, seed=None)

Bases: torch.nn.modules.module.Module

Abstract model class intended for ease of implementation in designing neural networks for data poisoning attacks. Requires an architecture to be defined in the form of a list or nested list containing the sequence of torch.nn.modules objects needed to perform a forward pass.

NOTE: If cuda is available, the class/model will be automatically sent to torch.device(“cuda”).

Parameters

• architecture (list) – list or nested list containing sequence of nn.torch.modules objects to be used in the forward pass of the model.

• optimizer (str) – String specifying optimizer to use in training neural network. Options: “adam”: torch.optim.Adam(), “adagrad”: torch.optim.Adagrad(), “adamax”: torch.optim.Adamax(), “sgd”: torch.optim.SGD().

• loss_func (str) – String specifying loss function to use in training neural network. Options: “mse”: nn.MSELoss(), “nll”: nn.NLLLoss(), “bce”: nn.BCELoss(), “cross_entropy”: nn.CrossEntropyLoss().

• lr (float) – Learning rate to use in training neural network.

• optim_kwargs (dict) – dictionary containing additional optimizer key-word arguments (Default = {}).

• loss_kwargs (dict) – dictionary containing additional key-word arguments for the loss function (Default = {}).

__init__(architecture: list, optimizer: str, loss_func: str, lr: float, optim_kwargs={}, loss_kwargs={}, seed=None)

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

Methods

__init__(architecture, optimizer, loss_func, lr)	Initializes internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Adds a child module to the current module.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Returns an iterator over module buffers.
children()	Returns an iterator over immediate children modules.
cpu()	Moves all model parameters and buffers to the CPU.
cuda([device])	Moves all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Sets the module in evaluation mode.
evaluate(X_test, y_test)	Compute evaluation metric on some test data.
extra_repr()	Set the extra representation of the module
float()	Casts all floating point parameters and buffers to float datatype.
forward(x)	Perform a forward pass through the model.
get_buffer(target)	Returns the buffer given by target if it exists, otherwise throws an error.
get_extra_state()	Returns any extra state to include in the module's state_dict.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
half()	Casts all floating point parameters and buffers to half datatype.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
modules()	Returns an iterator over all modules in the network.
named_buffers([prefix, recurse])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Returns an iterator over module parameters.
register_backward_hook(hook)	Registers a backward hook on the module.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_forward_hook(hook)	Registers a forward hook on the module.
register_forward_pre_hook(hook)	Registers a forward pre-hook on the module.
register_full_backward_hook(hook)	Registers a backward hook on the module.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Adds a parameter to the module.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	This function is called from load_state_dict() to handle any extra state found within the state_dict.
share_memory()	See torch.Tensor.share_memory_()
state_dict([destination, prefix, keep_vars])	Returns a dictionary containing a whole state of the module.
step(X_batch, y_batch)	Perform a step of gradient descent on the passed inputs (X_batch) and labels (y_batch).
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
train([mode])	Sets the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Moves all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.

Attributes

T_destination	alias of TypeVar('T_destination', bound=Mapping[str, torch.Tensor])
dump_patches	This allows better BC support for load_state_dict().

evaluate(X_test, y_test)

Compute evaluation metric on some test data.

Parameters

• X_test (np.ndarray or torch.Tensor) – test input data.

• y_test (np.ndarray or torch.Tensor) – test target data.

Returns

evaluation metric.

Return type

(np.ndarray or torch.Tensor)

forward(x)

Perform a forward pass through the model.

Parameters

x (np.ndarray or torch.Tensor) – Input array of shape (batch_size, input_shape).

Returns

Predictions from current state of

the model.

Return type

(np.ndarray or torch.Tensor)

step(X_batch, y_batch)

Perform a step of gradient descent on the passed inputs (X_batch) and labels (y_batch). The inputs and labels are automatiucally

Parameters

• X_batch (np.ndarray, torch.Tensor) – input data used in training.

• y_batch (np.ndarray, torch.Tensor) – target data used in training.