- class avalanche.training.templates.BaseTemplate(model: Module, device: str | device = 'cpu', plugins: Sequence[BasePlugin] | None = None)[source]
Base class for continual learning skeletons.
Training loop The training loop is organized as follows:
train train_exp # for each experience
Evaluation loop The evaluation loop is organized as follows:
eval eval_exp # for each experience
- __init__(model: Module, device: str | device = 'cpu', plugins: Sequence[BasePlugin] | None = None)[source]
__init__(model[, device, plugins])
Evaluate the current model on a series of experiences and returns the last recorded value for each metric.
True if the strategy is in evaluation mode.
PyTorch device where the model will be allocated.
List of `SupervisedPlugin`s. .
True if the strategy is in training mode.
Current evaluation stream.