zoo

LinearRegression(loss_fn='mse', optimizer_fn='sgd', lr=0.001, device='cpu', seed=42, is_feature_incremental=False, **kwargs)

Bases: Regressor

This class implements a linear regression model in PyTorch.

MultiLayerPerceptron(n_width=5, n_layers=5, loss_fn='mse', optimizer_fn='sgd', lr=0.001, is_feature_incremental=True, device='cpu', seed=42, **kwargs)

Bases: Regressor

This class implements a logistic regression model in PyTorch.

PARAMETER	DESCRIPTION
n_width	Number of units in each hidden layer. TYPE: int DEFAULT: 5
n_layers	Number of hidden layers. TYPE: int DEFAULT: 5
loss_fn	Loss function to be used for training the wrapped model. Can be a loss function provided by `torch.nn.functional` or one of the following: 'mse', 'l1', 'cross_entropy', 'binary_cross_entropy_with_logits', 'binary_crossentropy', 'smooth_l1', 'kl_div'. TYPE: Union[str, Callable] DEFAULT: 'mse'
optimizer_fn	Optimizer to be used for training the wrapped model. Can be an optimizer class provided by torch.optim or one of the following: "adam", "adam_w", "sgd", "rmsprop", "lbfgs". TYPE: Union[str, 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.
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: True
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: {}