TRAINING

Functions

utils.training.initialize_wandb(args)

Initializes wandb, if installed.

Parameters:

args (Namespace) – the arguments of the current execution

utils.training.train(model, dataset, args)

The training process, including evaluations and loggers.

Parameters:

• model (ContinualModel) – the module to be trained

• dataset (ContinualDataset) – the continual dataset at hand

• args (Namespace) – the arguments of the current execution

utils.training.train_single_epoch(model, train_loader, args, epoch, pbar, system_tracker=None, scheduler=None)

Trains the model for a single epoch.

Parameters:

• model (ContinualModel) – the model to be trained

• train_loader (Iterable) – the data loader for the training set

• args (Namespace) – the arguments from the command line

• epoch (int) – the current epoch

• system_tracker – the system tracker to monitor the system stats

• scheduler – the scheduler for the current epoch

Returns:

the number of iterations performed in the current epoch

Return type:

int