ConvTranRegressorTorch
ConvTran regressor in PyTorch.
Quickstart
from sktime.regression.deep_learning.convtran import ConvTranRegressorTorch
estimator = ConvTranRegressorTorch(net_type: str='C-T', activation: str | None | Callable=None, activation_hidden: str='relu', emb_size: int=16, dim_ff: int=256, num_heads: int=8, dropout: float=0.01, use_abs_pos_encoding: bool=True, use_rel_pos_encoding: bool=True, abs_pos_encoding_scheme: str | None='tAPE', rel_pos_encoding_scheme: str | None='erpe', num_epochs: int=100, batch_size: int=1, optimizer: str | None | Callable='RMSprop', criterion: str | None | Callable='MSELoss', callbacks: None | str | tuple [str, ... ]='ReduceLROnPlateau', optimizer_kwargs: dict | None=None, criterion_kwargs: dict | None=None, callback_kwargs: dict | None=None, lr: float=0.001, verbose: bool=False, random_state: int=0)Parameters(22)
- net_typestr, default=”C-T”
- Network type to use. Should be one of “T” (Transformer), “C-T” (ConvTran) or “C-CT” (Causal ConvTran).
- activationstr or None, default=None
- Activation function to use in the output layer.
- activation_hiddenstr, default=”relu”
- Activation function to use in the hidden layers.
- emb_sizeint, default=16
- Embedding dimension used in attention and feed-forward blocks.
- dim_ffint, default=256
- Hidden dimension of the feed-forward block.
- num_headsint, default=8
- Number of attention heads.
- dropoutfloat, default=0.01
- Dropout rate applied in attention and feed-forward blocks.
- use_abs_pos_encodingbool, default=True
- Whether to apply absolute positional encoding.
- use_rel_pos_encodingbool, default=True
- Whether to apply relative positional encoding.
- abs_pos_encoding_schemestr or None, default=”tAPE”
- Absolute positional encoding scheme. Supported values: “tAPE”, “sin”, “learn”, or None.
- rel_pos_encoding_schemestr or None, default=”erpe”
- Relative positional encoding scheme. Supported values: “erpe”, “vector”, or None.
- num_epochsint, default = 100
- The number of epochs to train the model.
- batch_sizeint, default = 1
- The size of each mini-batch during training.
- optimizerstr or None or an instance of optimizers
defined in torch.optim, default = “RMSprop” The optimizer to use for training the model. List of available optimizers: https://pytorch.org/docs/stable/optim.html#algorithms
- criterioncase insensitive str or None or an instance of a loss function
defined in PyTorch, default = “MSELoss” The loss function to be used in training the neural network. List of available loss functions: https://pytorch.org/docs/stable/nn.html#loss-functions
- callbacksNone or str or a tuple of str, default = “ReduceLROnPlateau”
Learning rate schedulers applied during training. Currently only learning rate schedulers are supported as callbacks. If more than one scheduler is passed, they are applied sequentially in the order they are passed. If None, then no learning rate scheduler is used. Note: Since PyTorch learning rate schedulers need to be initialized with the optimizer object, we only accept the class name (str) of the scheduler here and do not accept an instance of the scheduler. As that can lead to errors and unexpected behavior. List of available learning rate schedulers: https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
- optimizer_kwargsdict or None, default = None
- Additional keyword arguments to pass to the optimizer.
- criterion_kwargsdict or None, default = None
- Additional keyword arguments to pass to the loss function.
- callback_kwargsdict or None, default = None
- The keyword arguments to be passed to the callbacks.
- lrfloat, default = 0.001
- The learning rate to use for the optimizer.
- verbosebool, default = False
- Whether to print progress information during training.
- random_stateint, default = 0
- Seed to ensure reproducibility.
Examples
>>> from sktime.regression.deep_learning.convtran import ConvTranRegressorTorch
>>> from sktime.datasets import load_unit_test
>>> X_train, y_train = load_unit_test (split = "train")
>>> X_test, y_test = load_unit_test (split = "test")
>>> reg = ConvTranRegressorTorch (num_epochs = 20, batch_size = 4)
>>> reg. fit (X_train, y_train) ConvTranRegressorTorch(
... )