composer.algorithms.label_smoothing.label_smoothing#
Core Label Smoothing classes and functions.
Functions
Shrinks targets towards a uniform distribution to counteract label noise as in Szegedy et al. |
Classes
Shrinks targets towards a uniform distribution to counteract label noise as in Szegedy et al. |
- class composer.algorithms.label_smoothing.label_smoothing.LabelSmoothing(alpha)[source]#
Bases:
composer.core.algorithm.Algorithm
Shrinks targets towards a uniform distribution to counteract label noise as in Szegedy et al.
This is computed by (1 - alpha) * targets + alpha * smoothed_targets where smoothed_targets is a vector of ones.
Introduced in Rethinking the Inception Architecture for Computer Vision.
Example
from composer.algorithms import LabelSmoothing from composer.trainer import Trainer label_smoothing_algorithm = LabelSmoothing(alpha=0.1) trainer = Trainer( model=model, train_dataloader=train_dataloader, eval_dataloader=eval_dataloader, max_duration="1ep", algorithms=[label_smoothing_algorithm], optimizers=[optimizer] )
- Parameters
alpha โ Strength of the label smoothing, in [0, 1].
alpha=0
means no label smoothing, andalpha=1
means maximal smoothing (targets are ignored).
- composer.algorithms.label_smoothing.label_smoothing.smooth_labels(logits, targets, alpha)[source]#
Shrinks targets towards a uniform distribution to counteract label noise as in Szegedy et al.
This is computed by (1 - alpha) * targets + alpha * smoothed_targets where smoothed_targets is a uniform distribution.
Example
from composer.algorithms.label_smoothing import smooth_labels new_targets = smooth_labels( logits=logits, targets=y_example, alpha=0.1 )
- Parameters
logits โ Output of the model. Tensor of shape (N, C, d1, โฆ, dn) for N examples and C classes, and d1, โฆ, dn extra dimensions.
targets โ Tensor of shape (N) containing integers 0 <= i <= C-1 specifying the target labels for each example.
alpha โ Strength of the label smoothing, in [0, 1].
alpha=0
means no label smoothing, andalpha=1
means maximal smoothing (targets are ignored).