tf.compat.v1.losses.log_loss | TensorFlow v2.16.1 (original) (raw)
tf.compat.v1.losses.log_loss
Adds a Log Loss term to the training procedure.
tf.compat.v1.losses.log_loss(
labels,
predictions,
weights=1.0,
epsilon=1e-07,
scope=None,
loss_collection=ops.GraphKeys.LOSSES,
reduction=Reduction.SUM_BY_NONZERO_WEIGHTS
)
weights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If weights 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 weights vector. If the shape ofweights matches the shape of predictions, then the loss of each measurable element of predictions is scaled by the corresponding value ofweights.
| Args | |
|---|---|
| labels | The ground truth output tensor, same dimensions as 'predictions'. |
| predictions | The predicted outputs. |
| weights | Optional Tensor whose rank is either 0, or the same rank aslabels, and must be broadcastable to labels (i.e., all dimensions must be either 1, or the same as the corresponding losses dimension). |
| epsilon | A small increment to add to avoid taking a log of zero. |
| scope | The scope for the operations performed in computing the loss. |
| loss_collection | collection to which the loss will be added. |
| reduction | Type of reduction to apply to loss. |
| Returns |
|---|
| Weighted loss float Tensor. If reduction is NONE, this has the same shape as labels; otherwise, it is scalar. |
| Raises | |
|---|---|
| ValueError | If the shape of predictions doesn't match that of labels or if the shape of weights is invalid. Also if labels or predictionsis None. |
eager compatibility
The loss_collection argument is ignored when executing eagerly. Consider holding on to the return value or collecting losses via a tf.keras.Model.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.