avalanche.training.JointTraining

class avalanche.training.JointTraining(model: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, criterion, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: int = 1, device='cpu', plugins: ~typing.Optional[~typing.Sequence[SupervisedPlugin]] = None, evaluator=<avalanche.training.plugins.evaluation.EvaluationPlugin object>, eval_every=-1)[source]

Joint training on the entire stream.

JointTraining performs joint training (also called offline training) on the entire stream of data. This means that it is not a continual learning strategy but it can be used as an “offline” upper bound for them.

__init__(model: ~torch.nn.modules.module.Module, optimizer: ~torch.optim.optimizer.Optimizer, criterion, train_mb_size: int = 1, train_epochs: int = 1, eval_mb_size: int = 1, device='cpu', plugins: ~typing.Optional[~typing.Sequence[SupervisedPlugin]] = None, evaluator=<avalanche.training.plugins.evaluation.EvaluationPlugin object>, eval_every=-1)[source]

Init.

Parameters
  • model – PyTorch model.

  • optimizer – PyTorch optimizer.

  • criterion – loss function.

  • train_mb_size – mini-batch size for training.

  • train_epochs – number of training epochs.

  • eval_mb_size – mini-batch size for eval.

  • device – PyTorch device to run the model.

  • plugins – (optional) list of StrategyPlugins.

  • evaluator – (optional) instance of EvaluationPlugin for logging and metric computations. None to remove logging.

  • 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__(model, optimizer, criterion[, ...])

Init.

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, ...])

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 strategy's model for all experiences.

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)

Concatenates all the datastream.

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.