tfa.losses.LiftedStructLoss

Computes the lifted structured loss.

tfa.losses.LiftedStructLoss(
    margin: tfa.types.FloatTensorLike = 1.0,
    name: Optional[str] = None,
    **kwargs
)

The loss encourages the positive distances (between a pair of embeddings with the same labels) to be smaller than any negative distances (between a pair of embeddings with different labels) in the mini-batch in a way that is differentiable with respect to the embedding vectors. See: https://arxiv.org/abs/1511.06452

margin Float, margin term in the loss definition.
name Optional name for the op.

Methods

from_config

@classmethod
from_config(
    config
)

Instantiates a Loss from its config (output of get_config()).

Args
config Output of get_config().

Returns
A Loss instance.

get_config

View source

get_config()

Returns the config dictionary for a Loss instance.

__call__

__call__(
    y_true, y_pred, sample_weight=None
)

Invokes the Loss instance.

Args
y_true Ground truth values. shape = [batch_size, d0, .. dN], except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]
y_pred The predicted values. shape = [batch_size, d0, .. dN]
sample_weight Optional sample_weight acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each loss element of y_pred is scaled by the corresponding value of sample_weight. (Note ondN-1: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns
Weighted loss float Tensor. If reduction is NONE, this has shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1 because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises
ValueError If the shape of sample_weight is invalid.