zoo

LSTMClassifierInitialized(n_features=10, loss_fn='binary_cross_entropy_with_logits', optimizer_fn='sgd', lr=0.001, output_is_logit=True, is_feature_incremental=False, device='cpu', seed=42, **kwargs)

Bases: RollingClassifierInitialized

A specialized LSTM-based classifier designed for handling rolling or incremental data classification tasks.

This class leverages LSTM (Long Short-Term Memory) modules to process and classify sequential data. It is built on top of the base RollingClassifierInitialized class, inheriting its functionality for handling incremental learning tasks. Customization options include the definition of the loss function, optimizer, learning rate, and other hyperparameters to suit various use cases.

ATTRIBUTE	DESCRIPTION
n_features	Number of features in the input data. It defines the input dimension for the LSTM module. TYPE: int
loss_fn	Specifies the loss function to be used for model training. Can either be a predefined string or a callable function. TYPE: Union[str, Callable]
optimizer_fn	Defines the optimizer to be utilized in training. Accepts either a string representing the optimizer name or the optimizer class itself. TYPE: Union[str, Type[Optimizer]]
lr	Learning rate for the chosen optimizer. TYPE: float
output_is_logit	Indicates whether the model output is a raw logit (pre-sigmoid/softmax output). TYPE: bool
is_feature_incremental	Specifies if the model supports adding new features incrementally. TYPE: bool
device	Designates the device for computation, e.g., 'cpu' or 'cuda'. TYPE: str
seed	Random seed for reproducibility of results. TYPE: int
kwargs	Additional arguments passed during the initialization. TYPE: dict

LogisticRegressionInitialized(n_features=10, loss_fn='binary_cross_entropy_with_logits', optimizer_fn='sgd', lr=0.001, output_is_logit=True, is_feature_incremental=False, device='cpu', seed=42, **kwargs)

Bases: ClassifierInitialized

Logistic Regression model for classification.

PARAMETER	DESCRIPTION
loss_fn	Loss function to be used for training the wrapped model. TYPE: str or Callable DEFAULT: 'binary_cross_entropy_with_logits'
optimizer_fn	Optimizer to be used for training the wrapped model. TYPE: str or Callable DEFAULT: 'sgd'
lr	Learning rate of the optimizer. TYPE: float DEFAULT: 0.001
output_is_logit	Whether the module produces logits as output. If true, either softmax or sigmoid is applied to the outputs when predicting. TYPE: bool DEFAULT: True
is_class_incremental	Whether the classifier should adapt to the appearance of previously unobserved classes by adding an unit to the output layer of the network. TYPE: bool
is_feature_incremental	Whether the model should adapt to the appearance of previously features by adding units to the input layer of the network. TYPE: bool DEFAULT: False
device	Device to run the wrapped model on. Can be "cpu" or "cuda". TYPE: str DEFAULT: 'cpu'
seed	Random seed to be used for training the wrapped model. TYPE: int DEFAULT: 42
**kwargs	Parameters to be passed to the build_fn function aside from n_features. DEFAULT: {}

MultiLayerPerceptronInitialized(n_features=10, n_width=5, n_layers=5, loss_fn='binary_cross_entropy_with_logits', optimizer_fn='sgd', lr=0.001, output_is_logit=True, is_feature_incremental=False, device='cpu', seed=42, **kwargs)

Bases: ClassifierInitialized

Logistic Regression model for classification.

PARAMETER	DESCRIPTION
loss_fn	Loss function to be used for training the wrapped model. TYPE: str or Callable DEFAULT: 'binary_cross_entropy_with_logits'
optimizer_fn	Optimizer to be used for training the wrapped model. TYPE: str or Callable DEFAULT: 'sgd'
lr	Learning rate of the optimizer. TYPE: float DEFAULT: 0.001
output_is_logit	Whether the module produces logits as output. If true, either softmax or sigmoid is applied to the outputs when predicting. TYPE: bool DEFAULT: True
is_class_incremental	Whether the classifier should adapt to the appearance of previously unobserved classes by adding an unit to the output layer of the network. TYPE: bool
is_feature_incremental	Whether the model should adapt to the appearance of previously features by adding units to the input layer of the network. TYPE: bool DEFAULT: False
device	Device to run the wrapped model on. Can be "cpu" or "cuda". TYPE: str DEFAULT: 'cpu'
seed	Random seed to be used for training the wrapped model. TYPE: int DEFAULT: 42
**kwargs	Parameters to be passed to the build_fn function aside from n_features. DEFAULT: {}