MLPNet

class MLPNet(input_size: int, hidden_size: List[int], lr: float, loss: torch.nn.modules.module.Module, optimizer_params: Optional[dict])

Bases: etna.models.base.DeepBaseNet

MLP model.

Init MLP model.

Parameters

• input_size (int) – size of the input feature space: target plus extra features

• hidden_size (List[int]) – list of sizes of the hidden states

• lr (float) – learning rate

• loss (torch.nn.Module) – loss function

• optimizer_params (Optional[dict]) – parameters for optimizer for Adam optimizer (api reference torch.optim.Adam)

Return type

None

Methods

configure_optimizers()	Optimizer configuration.
forward(batch)	Forward pass.
make_samples(df, encoder_length, decoder_length)	Make samples from segment DataFrame.
step(batch, *args, **kwargs)	Step for loss computation for training or validation.

Attributes

configure_optimizers()

Optimizer configuration.

forward(batch: etna.models.nn.mlp.MLPBatch)

Forward pass.

Parameters

batch (etna.models.nn.mlp.MLPBatch) – batch of data

Returns

forecast

make_samples(df: pandas.core.frame.DataFrame, encoder_length: int, decoder_length: int) → Iterable[dict]

Make samples from segment DataFrame.

Parameters

• df (pandas.core.frame.DataFrame) –

• encoder_length (int) –

• decoder_length (int) –

Return type

Iterable[dict]

step(batch: etna.models.nn.mlp.MLPBatch, *args, **kwargs)

Step for loss computation for training or validation.

Parameters

batch (etna.models.nn.mlp.MLPBatch) – batch of data

Returns

loss, true_target, prediction_target