View source on GitHub |
Computes the contrastive loss between y_true
and y_pred
.
tfa.losses.ContrastiveLoss(
margin: tfa.types.Number
= 1.0,
reduction: str = tf.keras.losses.Reduction.SUM_OVER_BATCH_SIZE,
name: str = 'contrastive_loss'
)
This loss encourages the embedding to be close to each other for the samples of the same label and the embedding to be far apart at least by the margin constant for the samples of different labels.
See: http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
We expect labels y_true
to be provided as 1-D integer Tensor
with shape [batch_size]
of binary integer labels. And y_pred
must be
1-D float Tensor
with shape [batch_size]
of distances between two
embedding matrices.
The euclidean distances y_pred
between two embedding matrices
a
and b
with shape [batch_size, hidden_size]
can be computed
as follows:
a = tf.constant([[1, 2],
[3, 4],[5, 6]], dtype=tf.float16)
b = tf.constant([[5, 9],
[3, 6],[1, 8]], dtype=tf.float16)
y_pred = tf.linalg.norm(a - b, axis=1)
y_pred
<tf.Tensor: shape=(3,), dtype=float16, numpy=array([8.06 , 2. , 4.473],
dtype=float16)>
<... Note: constants a & b have been used purely for example purposes and have no significant value ...>
Args | |
---|---|
margin
|
Float , margin term in the loss definition.
Default value is 1.0.
|
reduction
|
(Optional) Type of tf.keras.losses.Reduction to apply.
Default value is SUM_OVER_BATCH_SIZE .
|
name
|
(Optional) name for the loss. |
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
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.
|