TensorFlow函数教程:tf.nn.quantized_relu_x

2019-01-31 13:51 更新

tf.nn.quantized_relu_x函数

tf.nn.quantized_relu_x(
    features,
    max_value,
    min_features,
    max_features,
    out_type=tf.quint8,
    name=None
)

请参阅指南:神经网络>候选采样

计算量化校正线性X: min(max(features, 0), max_value)

参数:

  • features:一个Tensor,必须是下列类型之一:qint8,quint8,qint32,qint16,quint16.
  • max_value:一个Tensor,类型为float32.
  • min_features:一个Tensor,类型为float32.最小量化值表示的浮点值.
  • max_features:一个Tensor,类型为float32.最大量化值表示的浮点值.
  • out_type:可选的tf.DType,可以是:tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16.默认为tf.quint8.
  • name:操作的名称(可选).

返回:

Tensor对象的元组(activations, min_activations, max_activations).

  • activations:一个Tensor,类型为out_type.
  • min_activations:一个Tensor,类型为float32.
  • max_activations:一个Tensor,类型为float32.
以上内容是否对您有帮助:
在线笔记
App下载
App下载

扫描二维码

下载编程狮App

公众号
微信公众号

编程狮公众号

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy