TensorFlow 1 version | View source on GitHub |
Loss base class.
tf.keras.losses.Loss(
reduction=losses_utils.ReductionV2.AUTO, name=None
)
To be implemented by subclasses:
call()
: Contains the logic for loss calculation usingy_true
,y_pred
.
Example subclass implementation:
class MeanSquaredError(Loss):
def call(self, y_true, y_pred):
y_pred = ops.convert_to_tensor(y_pred)
y_true = math_ops.cast(y_true, y_pred.dtype)
return K.mean(math_ops.square(y_pred - y_true), axis=-1)
When used with tf.distribute.Strategy
, outside of built-in training loops
such as tf.keras
compile
and fit
, please use 'SUM' or 'NONE' reduction
types, and reduce losses explicitly in your training loop. Using 'AUTO' or
'SUM_OVER_BATCH_SIZE' will raise an error.
Please see https://www.tensorflow.org/tutorials/distribute/custom_training for more details on this.
You can implement 'SUM_OVER_BATCH_SIZE' using global batch size like:
with strategy.scope():
loss_obj = tf.keras.losses.CategoricalCrossentropy(
reduction=tf.keras.losses.Reduction.NONE)
....
loss = (tf.reduce_sum(loss_obj(labels, predictions)) *
(1. / global_batch_size))
Args | |
---|---|
reduction
|
(Optional) 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 with tf.distribute.Strategy , outside of built-in training
loops such as tf.keras compile and fit , using AUTO or
SUM_OVER_BATCH_SIZE will raise an error. Please see
https://www.tensorflow.org/tutorials/distribute/custom_training
for more details on this.
|
name
|
Optional name for the op. |
Methods
call
@abc.abstractmethod
call( y_true, y_pred )
Invokes the Loss
instance.
Args | |
---|---|
y_true
|
Ground truth values, with the same shape as 'y_pred'. |
y_pred
|
The predicted values. |
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
get_config()
__call__
__call__(
y_true, y_pred, sample_weight=None
)
Invokes the Loss
instance.
Args | |
---|---|
y_true
|
Ground truth values. shape = [batch_size, d0, .. dN]
|
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.
|