tf.raw_ops.CumulativeLogsumexp
bookmark_borderbookmark
Stay organized with collections
Save and categorize content based on your preferences.
Compute the cumulative product of the tensor x
along axis
.
View aliases
Compat aliases for migration
See
Migration guide for
more details.
tf.compat.v1.raw_ops.CumulativeLogsumexp
tf.raw_ops.CumulativeLogsumexp(
x, axis, exclusive=False, reverse=False, name=None
)
By default, this op performs an inclusive cumulative log-sum-exp,
which means that the first
element of the input is identical to the first element of the output:
tf.math.cumulative_logsumexp([a, b, c]) # => [a, log(exp(a) + exp(b)), log(exp(a) + exp(b) + exp(c))]
By setting the exclusive
kwarg to True
, an exclusive cumulative log-sum-exp is
performed instead:
tf.cumulative_logsumexp([a, b, c], exclusive=True) # => [-inf, a, log(exp(a) * exp(b))]
Note that the neutral element of the log-sum-exp operation is -inf
,
however, for performance reasons, the minimal value representable by the
floating point type is used instead.
By setting the reverse
kwarg to True
, the cumulative log-sum-exp is performed in the
opposite direction.
Args |
x
|
A Tensor . Must be one of the following types: bfloat16 , half , float32 , float64 .
A Tensor . Must be one of the following types: float16 , float32 , float64 .
|
axis
|
A Tensor . Must be one of the following types: int32 , int64 .
A Tensor of type int32 (default: 0). Must be in the range
[-rank(x), rank(x)) .
|
exclusive
|
An optional bool . Defaults to False .
If True , perform exclusive cumulative log-sum-exp.
|
reverse
|
An optional bool . Defaults to False .
A bool (default: False).
|
name
|
A name for the operation (optional).
|
Returns |
A Tensor . Has the same type as x .
|
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-04-26 UTC."],[],[],null,["# tf.raw_ops.CumulativeLogsumexp\n\n\u003cbr /\u003e\n\nCompute the cumulative product of the tensor `x` along `axis`.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.raw_ops.CumulativeLogsumexp`](https://www.tensorflow.org/api_docs/python/tf/raw_ops/CumulativeLogsumexp)\n\n\u003cbr /\u003e\n\n tf.raw_ops.CumulativeLogsumexp(\n x, axis, exclusive=False, reverse=False, name=None\n )\n\nBy default, this op performs an inclusive cumulative log-sum-exp,\nwhich means that the first\nelement of the input is identical to the first element of the output: \n\n tf.math.cumulative_logsumexp([a, b, c]) # =\u003e [a, log(exp(a) + exp(b)), log(exp(a) + exp(b) + exp(c))]\n\nBy setting the `exclusive` kwarg to `True`, an exclusive cumulative log-sum-exp is\nperformed instead: \n\n tf.cumulative_logsumexp([a, b, c], exclusive=True) # =\u003e [-inf, a, log(exp(a) * exp(b))]\n\nNote that the neutral element of the log-sum-exp operation is `-inf`,\nhowever, for performance reasons, the minimal value representable by the\nfloating point type is used instead.\n\nBy setting the `reverse` kwarg to `True`, the cumulative log-sum-exp is performed in the\nopposite direction.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `x` | A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`. A `Tensor`. Must be one of the following types: `float16`, `float32`, `float64`. |\n| `axis` | A `Tensor`. Must be one of the following types: `int32`, `int64`. A `Tensor` of type `int32` (default: 0). Must be in the range `[-rank(x), rank(x))`. |\n| `exclusive` | An optional `bool`. Defaults to `False`. If `True`, perform exclusive cumulative log-sum-exp. |\n| `reverse` | An optional `bool`. Defaults to `False`. A `bool` (default: False). |\n| `name` | A name for the operation (optional). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor`. Has the same type as `x`. ||\n\n\u003cbr /\u003e"]]