MixUp

class composer.algorithms.MixUp(alpha=0.2, interpolate_loss=False, input_key=0, target_key=1)

MixUp trains the network on convex batch combinations.

The algorithm uses individual examples and targets to make a convex combination of a given batch X with a randomly permuted copy of X. The mixing coefficient is drawn from a Beta(alpha, alpha) distribution.

Training in this fashion sometimes reduces generalization error.

Parameters

• alpha (float, optional) – the psuedocount for the Beta distribution used to sample mixing parameters. As alpha grows, the two samples in each pair tend to be weighted more equally. As alpha approaches 0 from above, the combination approaches only using one element of the pair. Default: 0.2.

• interpolate_loss (bool, optional) – Interpolates the loss rather than the labels. A useful trick when using a cross entropy loss. Will produce incorrect behavior if the loss is not a linear function of the targets. Default: False

• input_key (str | int | tuple[Callable, Callable] | Any, optional) – A key that indexes to the input from the batch. Can also be a pair of get and set functions, where the getter is assumed to be first in the pair. The default is 0, which corresponds to any sequence, where the first element is the input. Default: 0.

• target_key (str | int | tuple[Callable, Callable] | Any, optional) – A key that indexes to the target from the batch. Can also be a pair of get and set functions, where the getter is assumed to be first in the pair. The default is 1, which corresponds to any sequence, where the second element is the target. Default: 1.

Example

from composer.algorithms import MixUp
algorithm = MixUp(alpha=0.2)
trainer = Trainer(
    model=model,
    train_dataloader=train_dataloader,
    eval_dataloader=eval_dataloader,
    max_duration="1ep",
    algorithms=[algorithm],
    optimizers=[optimizer]
)