diff options
author | A. Unique TensorFlower <nobody@tensorflow.org> | 2016-05-26 01:36:58 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-05-26 02:47:07 -0700 |
commit | 017175783ec4eead6c6c98a0e0de1e5031d45845 (patch) | |
tree | b2d8e34cb87bc86a2405d8182b4e28779e724c1e /tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md | |
parent | c963048b536b8905729ee617dfb78f21a0abd4d7 (diff) |
Update generated Python Op docs.
Change: 123300300
Diffstat (limited to 'tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md')
-rw-r--r-- | tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md b/tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md new file mode 100644 index 0000000000..ea710b2a15 --- /dev/null +++ b/tensorflow/g3doc/api_docs/python/functions_and_classes/shard9/tf.gradients.md @@ -0,0 +1,48 @@ +### `tf.gradients(ys, xs, grad_ys=None, name='gradients', colocate_gradients_with_ops=False, gate_gradients=False, aggregation_method=None)` {#gradients} + +Constructs symbolic partial derivatives of sum of `ys` w.r.t. x in `xs`. + +`ys` and `xs` are each a `Tensor` or a list of tensors. `grad_ys` +is a list of `Tensor`, holding the gradients received by the +`ys`. The list must be the same length as `ys`. + +`gradients()` adds ops to the graph to output the partial +derivatives of `ys` with respect to `xs`. It returns a list of +`Tensor` of length `len(xs)` where each tensor is the `sum(dy/dx)` +for y in `ys`. + +`grad_ys` is a list of tensors of the same length as `ys` that holds +the initial gradients for each y in `ys`. When `grad_ys` is None, +we fill in a tensor of '1's of the shape of y for each y in `ys`. A +user can provide their own initial `grad_ys` to compute the +derivatives using a different initial gradient for each y (e.g., if +one wanted to weight the gradient differently for each value in +each y). + +##### Args: + + +* <b>`ys`</b>: A `Tensor` or list of tensors to be differentiated. +* <b>`xs`</b>: A `Tensor` or list of tensors to be used for differentiation. +* <b>`grad_ys`</b>: Optional. A `Tensor` or list of tensors the same size as + `ys` and holding the gradients computed for each y in `ys`. +* <b>`name`</b>: Optional name to use for grouping all the gradient ops together. + defaults to 'gradients'. +* <b>`colocate_gradients_with_ops`</b>: If True, try colocating gradients with + the corresponding op. +* <b>`gate_gradients`</b>: If True, add a tuple around the gradients returned + for an operations. This avoids some race conditions. +* <b>`aggregation_method`</b>: Specifies the method used to combine gradient terms. + Accepted values are constants defined in the class `AggregationMethod`. + +##### Returns: + + A list of `sum(dy/dx)` for each x in `xs`. + +##### Raises: + + +* <b>`LookupError`</b>: if one of the operations between `x` and `y` does not + have a registered gradient function. +* <b>`ValueError`</b>: if the arguments are invalid. + |