tf.nn.relu_layer
Stay organized with collections
Save and categorize content based on your preferences.
Computes Relu(x * weight + biases).
tf.nn.relu_layer(
x, weights, biases, name=None
)
Args |
|---|
x
|
a 2D tensor. Dimensions typically: batch, in_units
|
weights
|
a 2D tensor. Dimensions typically: in_units, out_units
|
biases
|
a 1D tensor. Dimensions: out_units
|
name
|
A name for the operation (optional). If not specified
"nn_relu_layer" is used.
|
Returns |
|---|
|
A 2-D Tensor computing relu(matmul(x, weights) + biases).
Dimensions typically: batch, out_units.
|
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.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.nn.relu_layer\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/nn_impl.py#L479-L499) |\n\nComputes Relu(x \\* weight + biases).\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.nn.relu_layer`](/api_docs/python/tf/compat/v1/nn/relu_layer)\n\n\u003cbr /\u003e\n\n tf.nn.relu_layer(\n x, weights, biases, name=None\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------|--------------------------------------------------------------------------------|\n| `x` | a 2D tensor. Dimensions typically: batch, in_units |\n| `weights` | a 2D tensor. Dimensions typically: in_units, out_units |\n| `biases` | a 1D tensor. Dimensions: out_units |\n| `name` | A name for the operation (optional). If not specified \"nn_relu_layer\" is used. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A 2-D Tensor computing relu(matmul(x, weights) + biases). Dimensions typically: batch, out_units. ||\n\n\u003cbr /\u003e"]]
View source on GitHub