安装带有量化支持的Tensorflow [英] Install Tensorflow with Quantization Support

问题描述

这是我另一个问题的跟进: Tensorflow中8位量化出现错误

This is a follow-up of another question by me : Error with 8-bit Quantization in Tensorflow

基本上，我想安装具有8位量化支持的Tensorflow.目前，我在CentOS 7机器上(没有GPU支持)以pip安装方法安装了Tensorflow 0.9.

Basically, I would like to install the Tensorflow with 8-bit quantization support. Currently, I installed Tensorflow 0.9 with pip installation method on CentOS 7 machine (without GPU support).

我可以编译和运行Pete Warden博客文章中给出的代码.但是，我无法导入Pete Warden的回复中给出的功能.我想添加量化支持.我也没有在Tensorflow文档中找到有关量化部分的任何细节.

I could compile and run the codes as given in Pete Warden's blog post. But, I can't import the functions given in Pete Warden's reply. I would like to add the quantization support. I couldn't find any details about the quantization part in the Tensorflow documentation also.

任何人都可以分享有关操作细节的信息吗?

Can anybody share the details on how to do it?

推荐答案

出于时间考虑，我可以找出一种方法来做到这一点.但仍在等待任何TensorFlow开发人员的官方方法.

For time-being, I could figure out a method to do this. But still waiting for official method from any TensorFlow developers.

1. 首先安装tensorflow(我尝试了源代码安装和PIP安装，都很好)
2. 从Github存储库中获取tensorflow源，并转到tensorflow根目录(我将其称为tensorflow_root.
3. 现在按照 Pete Warden的博客

1. First install the tensorflow ( I tried both source installation as well as PIP installation, both are fine)
2. Get the tensorflow source from the Github repo and go to the tensorflow root directory (I would call it tensorflow_root.
3. Now compile the quantization script as given in Pete Warden's blog

bazel build tensorflow/contrib/quantization/tools:quantize_graph

这将为量化版本创建ops库.转到tensorflow_root/bazel-bin/tensorflow/contrib/quantization，您应该看到两个库文件:_quantized_ops.so和kernels/_quantized_kernels.so

This wil create ops libraries for quantized versions. Go to tensorflow_root/bazel-bin/tensorflow/contrib/quantization and you should see two library files : _quantized_ops.so and kernels/_quantized_kernels.so

1. 现在在脚本中，您应该与tensorflow一起使用专用的tensorflow函数导入这两个库文件

您可以使用 tf.load_op_library()函数

import tensorflow as tf
qops = tf.load_op_library('[tensorflow_root]/bazel-bin/tensorflow/contrib/quantization/_quantized_ops.so')
qkernelops = tf.load_op_library('[tensorflow_root]/bazel-bin/tensorflow/contrib/quantization/kernels/_quantized_kernels.so')

这篇关于安装带有量化支持的Tensorflow的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！