avalanche.benchmarks.utils.data_loader.ReplayDataLoader
- class avalanche.benchmarks.utils.data_loader.ReplayDataLoader(data: avalanche.benchmarks.utils.avalanche_dataset.AvalancheDataset, memory: typing.Optional[avalanche.benchmarks.utils.avalanche_dataset.AvalancheDataset] = None, oversample_small_tasks: bool = False, collate_mbatches=<function _default_collate_mbatches_fn>, batch_size: int = 32, force_data_batch_size: typing.Optional[int] = None, **kwargs)[source]
Custom data loader for rehearsal/replay strategies.
- __init__(data: avalanche.benchmarks.utils.avalanche_dataset.AvalancheDataset, memory: typing.Optional[avalanche.benchmarks.utils.avalanche_dataset.AvalancheDataset] = None, oversample_small_tasks: bool = False, collate_mbatches=<function _default_collate_mbatches_fn>, batch_size: int = 32, force_data_batch_size: typing.Optional[int] = None, **kwargs)[source]
Custom data loader for rehearsal strategies.
The iterates in parallel two datasets, the current data and the rehearsal memory, which are used to create mini-batches by concatenating their data together. Mini-batches from both of them are balanced using the task label (i.e. each mini-batch contains a balanced number of examples from all the tasks in the data and memory).
If oversample_small_tasks == True smaller tasks are oversampled to match the largest task.
- Parameters
data – AvalancheDataset.
memory – AvalancheDataset.
oversample_small_tasks – whether smaller tasks should be oversampled to match the largest one.
collate_mbatches – function that given a sequence of mini-batches (one for each task) combines them into a single mini-batch. Used to combine the mini-batches obtained separately from each task.
batch_size – the size of the batch. It must be greater than or equal to the number of tasks.
ratio_data_mem – How many of the samples should be from
kwargs – data loader arguments used to instantiate the loader for each task separately. See pytorch
DataLoader
.
Methods
__init__
(data[, memory, ...])Custom data loader for rehearsal strategies.