提交 c0637048 编写于 作者: A A. Unique TensorFlower 提交者: TensorFlower Gardener

Update generated Python Op docs.

Change: 128894163
上级 0d534ca6
......@@ -140,6 +140,31 @@ Notice that the function adds the given losses to the regularization losses.
* <b>`ValueError`</b>: if `losses` is not iterable.
- - -
### `tf.contrib.losses.hinge_loss(logits, target, scope=None)` {#hinge_loss}
Method that returns the loss tensor for hinge loss.
##### Args:
* <b>`logits`</b>: The logits, a float tensor.
* <b>`target`</b>: The ground truth output tensor. Its shape should match the shape of
logits. The values of the tensor are expected to be 0.0 or 1.0.
* <b>`scope`</b>: The scope for the operations performed in computing the loss.
##### Returns:
A `Tensor` of same shape as logits and target representing the loss values
across the batch.
##### Raises:
* <b>`ValueError`</b>: If the shapes of `logits` and `target` don't match.
- - -
### `tf.contrib.losses.log_loss(predictions, targets, weight=1.0, epsilon=1e-07, scope=None)` {#log_loss}
......
### `tf.contrib.losses.hinge_loss(logits, target, scope=None)` {#hinge_loss}
Method that returns the loss tensor for hinge loss.
##### Args:
* <b>`logits`</b>: The logits, a float tensor.
* <b>`target`</b>: The ground truth output tensor. Its shape should match the shape of
logits. The values of the tensor are expected to be 0.0 or 1.0.
* <b>`scope`</b>: The scope for the operations performed in computing the loss.
##### Returns:
A `Tensor` of same shape as logits and target representing the loss values
across the batch.
##### Raises:
* <b>`ValueError`</b>: If the shapes of `logits` and `target` don't match.
......@@ -745,6 +745,7 @@
* [`get_losses`](../../api_docs/python/contrib.losses.md#get_losses)
* [`get_regularization_losses`](../../api_docs/python/contrib.losses.md#get_regularization_losses)
* [`get_total_loss`](../../api_docs/python/contrib.losses.md#get_total_loss)
* [`hinge_loss`](../../api_docs/python/contrib.losses.md#hinge_loss)
* [`log_loss`](../../api_docs/python/contrib.losses.md#log_loss)
* [`sigmoid_cross_entropy`](../../api_docs/python/contrib.losses.md#sigmoid_cross_entropy)
* [`softmax_cross_entropy`](../../api_docs/python/contrib.losses.md#softmax_cross_entropy)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册