tf.raw_ops.QuantizedBatchNormWithGlobalNormalization
bookmark_borderbookmark
Stay organized with collections
Save and categorize content based on your preferences.
Quantized Batch normalization.
View aliases
Compat aliases for migration
See
Migration guide for
more details.
tf.compat.v1.raw_ops.QuantizedBatchNormWithGlobalNormalization
tf.raw_ops.QuantizedBatchNormWithGlobalNormalization(
t,
t_min,
t_max,
m,
m_min,
m_max,
v,
v_min,
v_max,
beta,
beta_min,
beta_max,
gamma,
gamma_min,
gamma_max,
out_type,
variance_epsilon,
scale_after_normalization,
name=None
)
This op is deprecated and will be removed in the future. Prefer
tf.nn.batch_normalization.
Args |
|---|
t
|
A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16.
A 4D input Tensor.
|
t_min
|
A Tensor of type float32.
The value represented by the lowest quantized input.
|
t_max
|
A Tensor of type float32.
The value represented by the highest quantized input.
|
m
|
A Tensor. Must have the same type as t.
A 1D mean Tensor with size matching the last dimension of t.
This is the first output from tf.nn.moments,
or a saved moving average thereof.
|
m_min
|
A Tensor of type float32.
The value represented by the lowest quantized mean.
|
m_max
|
A Tensor of type float32.
The value represented by the highest quantized mean.
|
v
|
A Tensor. Must have the same type as t.
A 1D variance Tensor with size matching the last dimension of t.
This is the second output from tf.nn.moments,
or a saved moving average thereof.
|
v_min
|
A Tensor of type float32.
The value represented by the lowest quantized variance.
|
v_max
|
A Tensor of type float32.
The value represented by the highest quantized variance.
|
beta
|
A Tensor. Must have the same type as t.
A 1D beta Tensor with size matching the last dimension of t.
An offset to be added to the normalized tensor.
|
beta_min
|
A Tensor of type float32.
The value represented by the lowest quantized offset.
|
beta_max
|
A Tensor of type float32.
The value represented by the highest quantized offset.
|
gamma
|
A Tensor. Must have the same type as t.
A 1D gamma Tensor with size matching the last dimension of t.
If "scale_after_normalization" is true, this tensor will be multiplied
with the normalized tensor.
|
gamma_min
|
A Tensor of type float32.
The value represented by the lowest quantized gamma.
|
gamma_max
|
A Tensor of type float32.
The value represented by the highest quantized gamma.
|
out_type
|
A tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16.
|
variance_epsilon
|
A float. A small float number to avoid dividing by 0.
|
scale_after_normalization
|
A bool.
A bool indicating whether the resulted tensor
needs to be multiplied with gamma.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A tuple of Tensor objects (result, result_min, result_max).
|
result
|
A Tensor of type out_type.
|
result_min
|
A Tensor of type float32.
|
result_max
|
A Tensor of type float32.
|
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.QuantizedBatchNormWithGlobalNormalization\n\n\u003cbr /\u003e\n\nQuantized Batch normalization.\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.QuantizedBatchNormWithGlobalNormalization`](https://www.tensorflow.org/api_docs/python/tf/raw_ops/QuantizedBatchNormWithGlobalNormalization)\n\n\u003cbr /\u003e\n\n tf.raw_ops.QuantizedBatchNormWithGlobalNormalization(\n t,\n t_min,\n t_max,\n m,\n m_min,\n m_max,\n v,\n v_min,\n v_max,\n beta,\n beta_min,\n beta_max,\n gamma,\n gamma_min,\n gamma_max,\n out_type,\n variance_epsilon,\n scale_after_normalization,\n name=None\n )\n\nThis op is deprecated and will be removed in the future. Prefer\n[`tf.nn.batch_normalization`](../../tf/nn/batch_normalization).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `t` | A `Tensor`. Must be one of the following types: `qint8`, `quint8`, `qint32`, `qint16`, `quint16`. A 4D input Tensor. |\n| `t_min` | A `Tensor` of type `float32`. The value represented by the lowest quantized input. |\n| `t_max` | A `Tensor` of type `float32`. The value represented by the highest quantized input. |\n| `m` | A `Tensor`. Must have the same type as `t`. A 1D mean Tensor with size matching the last dimension of t. This is the first output from tf.nn.moments, or a saved moving average thereof. |\n| `m_min` | A `Tensor` of type `float32`. The value represented by the lowest quantized mean. |\n| `m_max` | A `Tensor` of type `float32`. The value represented by the highest quantized mean. |\n| `v` | A `Tensor`. Must have the same type as `t`. A 1D variance Tensor with size matching the last dimension of t. This is the second output from tf.nn.moments, or a saved moving average thereof. |\n| `v_min` | A `Tensor` of type `float32`. The value represented by the lowest quantized variance. |\n| `v_max` | A `Tensor` of type `float32`. The value represented by the highest quantized variance. |\n| `beta` | A `Tensor`. Must have the same type as `t`. A 1D beta Tensor with size matching the last dimension of t. An offset to be added to the normalized tensor. |\n| `beta_min` | A `Tensor` of type `float32`. The value represented by the lowest quantized offset. |\n| `beta_max` | A `Tensor` of type `float32`. The value represented by the highest quantized offset. |\n| `gamma` | A `Tensor`. Must have the same type as `t`. A 1D gamma Tensor with size matching the last dimension of t. If \"scale_after_normalization\" is true, this tensor will be multiplied with the normalized tensor. |\n| `gamma_min` | A `Tensor` of type `float32`. The value represented by the lowest quantized gamma. |\n| `gamma_max` | A `Tensor` of type `float32`. The value represented by the highest quantized gamma. |\n| `out_type` | A [`tf.DType`](../../tf/dtypes/DType) from: `tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16`. |\n| `variance_epsilon` | A `float`. A small float number to avoid dividing by 0. |\n| `scale_after_normalization` | A `bool`. A bool indicating whether the resulted tensor needs to be multiplied with gamma. |\n| `name` | A name for the operation (optional). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|--------------|--------------------------------|\n| A tuple of `Tensor` objects (result, result_min, result_max). ||\n| `result` | A `Tensor` of type `out_type`. |\n| `result_min` | A `Tensor` of type `float32`. |\n| `result_max` | A `Tensor` of type `float32`. |\n\n\u003cbr /\u003e"]]
