SparseCategoricalCrossentropyIgnore

SparseCategoricalCrossentropyIgnore class

dlf.losses.sparse_categorial_crossentropy_ignore.SparseCategoricalCrossentropyIgnore(
    num_classes, name="sparse_categorical_crossentropy_ignore", from_logits=False
)

Implementation for sparse crossentropy loss with ignore label functionality.

The same implmentation like tf.keras.losses.SparseCategoricalCrossentropy but with the addtion that this implementation ignores all label ids <= num_classes.

Aliases

• SparseCategoricalCrossentropyIgnore
• sparse_categorical_crossentropy_ignore

Arguments

• num_classes: int. Number of classes, everthing above or equal will be ignored
• name: str, optonal, Name of the loss function. Defaults to 'sparse_categorical_crossentropy_ignore'.
• from_logits: bool. If true, y_pred is expected to be a logits tensor. Defaults to False.

Returns

A tf.keras.losses.Loss

YAML Configuration

loss:
    SparseCategoricalCrossentropyIgnore:
        num_classes: 7
        from_logits: False

---