avalanche.training.ICaRL

class avalanche.training.ICaRL(feature_extractor: ~torch.nn.modules.module.Module, classifier: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, memory_size, buffer_transform, fixed_memory, criterion=<avalanche.training.losses.ICaRLLossPlugin object>, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: ~typing.Optional[int] = None, device=None, plugins: ~typing.Optional[~typing.List[~avalanche.core.SupervisedPlugin]] = None, evaluator: ~avalanche.training.plugins.evaluation.EvaluationPlugin = <avalanche.training.plugins.evaluation.EvaluationPlugin object>, eval_every=-1)

iCaRL Strategy.

This strategy does not use task identities.

__init__(feature_extractor: ~torch.nn.modules.module.Module, classifier: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, memory_size, buffer_transform, fixed_memory, criterion=<avalanche.training.losses.ICaRLLossPlugin object>, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: ~typing.Optional[int] = None, device=None, plugins: ~typing.Optional[~typing.List[~avalanche.core.SupervisedPlugin]] = None, evaluator: ~avalanche.training.plugins.evaluation.EvaluationPlugin = <avalanche.training.plugins.evaluation.EvaluationPlugin object>, eval_every=-1)

Init.

Parameters

• feature_extractor – The feature extractor.

• classifier – The differentiable classifier that takes as input the output of the feature extractor.

• optimizer – The optimizer to use.

• memory_size – The nuber of patterns saved in the memory.

• buffer_transform – transform applied on buffer elements already modified by test_transform (if specified) before being used for replay

• fixed_memory – If True a memory of size memory_size is allocated and partitioned between samples from the observed experiences. If False every time a new class is observed memory_size samples of that class are added to the memory.

• 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.

Methods

__init__(feature_extractor, classifier, ...)	Init.
backward()	Run the backward pass.
criterion()	Loss function.
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, ...])	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()	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.