avalanche.training.MIR

class avalanche.training.MIR(*, model: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, criterion: ~torch.nn.modules.module.Module | ~typing.Callable[[~torch.Tensor, ~torch.Tensor], ~torch.Tensor], mem_size: int, subsample: int, batch_size_mem: int = 1, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: int = 1, device: str | ~torch.device = 'cpu', plugins: ~typing.List[~avalanche.core.SupervisedPlugin] | None = None, evaluator: ~avalanche.training.plugins.evaluation.EvaluationPlugin | ~typing.Callable[[], ~avalanche.training.plugins.evaluation.EvaluationPlugin] = <function default_evaluator>, eval_every=-1, **base_kwargs)[source]

Maximally Interfered Replay Strategy See ER_MIR plugin for details.

__init__(*, model: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, criterion: ~torch.nn.modules.module.Module | ~typing.Callable[[~torch.Tensor, ~torch.Tensor], ~torch.Tensor], mem_size: int, subsample: int, batch_size_mem: int = 1, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: int = 1, device: str | ~torch.device = 'cpu', plugins: ~typing.List[~avalanche.core.SupervisedPlugin] | None = None, evaluator: ~avalanche.training.plugins.evaluation.EvaluationPlugin | ~typing.Callable[[], ~avalanche.training.plugins.evaluation.EvaluationPlugin] = <function default_evaluator>, eval_every=-1, **base_kwargs)[source]

Init. :param model: The model. :param optimizer: The optimizer to use. :param criterion: The loss criterion to use. :param mem_size: Amount of fixed memory to use :param subsample: Size of the initial sample

from which to select the replay batch

Parameters:
  • batch_size_mem – Size of the replay batch after loss-based selection

  • train_mb_size – The train minibatch size. Defaults to 1.

  • train_epochs – The number of training epochs. Defaults to 1.

  • eval_mb_size – The eval minibatch size. Defaults to 1.

  • device – The device to use. Defaults to None (cpu).

  • plugins – Plugins to be added. Defaults to None.

  • evaluator – (optional) instance of EvaluationPlugin for logging and metric computations.

  • eval_every – the frequency of the calls to eval inside the training loop. -1 disables the evaluation. 0 means eval is called only at the end of the learning experience. Values >0 mean that eval is called every eval_every epochs and at the end of the learning experience.

  • **base_kwargs

    any additional BaseTemplate constructor arguments.

Methods

__init__(*, model, optimizer, criterion, ...)

Init. :param model: The model. :param optimizer: The optimizer to use. :param criterion: The loss criterion to use. :param mem_size: Amount of fixed memory to use :param subsample: Size of the initial sample from which to select the replay batch :param batch_size_mem: Size of the replay batch after loss-based selection :param train_mb_size: The train minibatch size. Defaults to 1. :param train_epochs: The number of training epochs. Defaults to 1. :param eval_mb_size: The eval minibatch size. Defaults to 1. :param device: The device to use. Defaults to None (cpu). :param plugins: Plugins to be added. Defaults to None. :param evaluator: (optional) instance of EvaluationPlugin for logging and metric computations. :param eval_every: the frequency of the calls to eval inside the training loop. -1 disables the evaluation. 0 means eval is called only at the end of the learning experience. Values >0 mean that eval is called every eval_every epochs and at the end of the learning experience. :param **base_kwargs: any additional BaseTemplate constructor arguments.

backward()

Run the backward pass.

check_model_and_optimizer([...])

criterion()

Loss function for supervised problems.

eval(exp_list, **kwargs)

Evaluate the current model on a series of experiences and returns the last recorded value for each metric.

eval_dataset_adaptation(**kwargs)

Initialize self.adapted_dataset.

eval_epoch(**kwargs)

Evaluation loop over the current self.dataloader.

forward()

Compute the model's output given the current mini-batch.

make_eval_dataloader([num_workers, shuffle, ...])

Initializes the eval data loader. :param num_workers: How many subprocesses to use for data loading. 0 means that the data will be loaded in the main process. (default: 0). :param pin_memory: If True, the data loader will copy Tensors into CUDA pinned memory before returning them. Defaults to True. :param kwargs: :return:.

make_optimizer([reset_optimizer_state, ...])

Optimizer initialization.

make_train_dataloader([num_workers, ...])

Data loader initialization.

model_adaptation([model])

Adapts the model to the current data.

optimizer_step()

Execute the optimizer step (weights update).

stop_training()

Signals to stop training at the next iteration.

train(experiences[, eval_streams])

Training loop.

train_dataset_adaptation(**kwargs)

Initialize self.adapted_dataset.

training_epoch(**kwargs)

Training epoch.

Attributes

is_eval

True if the strategy is in evaluation mode.

mb_task_id

Current mini-batch task labels.

mb_x

Current mini-batch input.

mb_y

Current mini-batch target.

mbatch

Current mini-batch.

mb_output

Model's output computed on the current mini-batch.

dataloader

Dataloader.

optimizer

PyTorch optimizer.

loss

Loss of the current mini-batch.

train_epochs

Number of training epochs.

train_mb_size

Training mini-batch size.

eval_mb_size

Eval mini-batch size.

retain_graph

Retain graph when calling loss.backward().

evaluator

EvaluationPlugin used for logging and metric computations.

clock

Incremental counters for strategy events.

adapted_dataset

Data used to train.

model

PyTorch model.

device

PyTorch device where the model will be allocated.

plugins

List of `SupervisedPlugin`s. .

experience

Current experience.

is_training

True if the strategy is in training mode.

current_eval_stream

Current evaluation stream.