tfa.seq2seq.SequenceLoss
Stay organized with collections
Save and categorize content based on your preferences.
Weighted cross-entropy loss for a sequence of logits.
tfa.seq2seq.SequenceLoss(
average_across_timesteps: bool = False,
average_across_batch: bool = False,
sum_over_timesteps: bool = True,
sum_over_batch: bool = True,
softmax_loss_function: Optional[Callable] = None,
name: Optional[str] = None
)
Args | |
|---|---|
reduction
|
Type of tf.keras.losses.Reduction to apply to
loss. Default value is AUTO. AUTO indicates that the reduction
option will be determined by the usage context. For almost all cases
this defaults to SUM_OVER_BATCH_SIZE. When used under a
tf.distribute.Strategy, except via Model.compile() and
Model.fit(), using AUTO or SUM_OVER_BATCH_SIZE
will raise an error. Please see this custom training tutorial
for more details.
|
name
|
Optional name for the instance. |
Methods
from_config
@classmethodfrom_config( config )
Instantiates a Loss from its config (output of get_config()).
| Args | |
|---|---|
config
|
Output of get_config().
|
| Returns | |
|---|---|
A Loss instance.
|
get_config
get_config()
Returns the config dictionary for a Loss instance.
__call__
__call__(
y_true, y_pred, sample_weight=None
)
Override the parent call to have a customized reduce behavior.