tf.raw_ops.EluGrad
Stay organized with collections
Save and categorize content based on your preferences.
Computes gradients for the exponential linear (Elu) operation.
tf.raw_ops.EluGrad(
gradients, outputs, name=None
)
Args |
gradients
|
A Tensor . Must be one of the following types: half , bfloat16 , float32 , float64 .
The backpropagated gradients to the corresponding Elu operation.
|
outputs
|
A Tensor . Must have the same type as gradients .
The outputs of the corresponding Elu operation.
|
name
|
A name for the operation (optional).
|
Returns |
A Tensor . Has the same type as gradients .
|
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.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf.raw_ops.EluGrad\n\n\u003cbr /\u003e\n\nComputes gradients for the exponential linear (Elu) operation.\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.EluGrad`](https://www.tensorflow.org/api_docs/python/tf/raw_ops/EluGrad)\n\n\u003cbr /\u003e\n\n tf.raw_ops.EluGrad(\n gradients, outputs, name=None\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `gradients` | A `Tensor`. Must be one of the following types: `half`, `bfloat16`, `float32`, `float64`. The backpropagated gradients to the corresponding Elu operation. |\n| `outputs` | A `Tensor`. Must have the same type as `gradients`. The outputs of the corresponding Elu operation. |\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 `gradients`. ||\n\n\u003cbr /\u003e"]]