如何在 ML.NET 上加载和运行 Intel-Tensorflow 模型 [英] How to load and run Intel-Tensorflow Model on ML.NET

问题描述

环境:Tensorflow 2.4、Intel-Tensorflow 2.4

据我所知，pb 格式的 Tensorflow 模型可以在 ML.NET 上加载.

但是，我使用的是量化包 LPOT (

您可以尝试在启用了英特尔 OneDNN 的 ML.NET 环境中安装 股票 Tensorflow 2.5.您可以从此链接安装库存 Tensorflow 轮:https://pypi.org/project/tensorflow/#文件

安装wheel文件:pip install __.whl.

要启用oneDNN优化，请设置环境变量TF_ENABLE_ONEDNN_OPTS:

设置 TF_ENABLE_ONEDNN_OPTS=1

要确保显示详细日志:set DNNL_VERBOSE=1

关于oneDNN详细模式的更多信息，请参考:https://oneapi-src.github.io/oneDNN/dev_guide_verbose.html

有关 tensorflow 的英特尔优化的更多信息，请参阅:https://software.intel.com/content/www/us/en/develop/articles/intel-optimization-for-tensorflow-installation-guide.html

Environment: Tensorflow 2.4, Intel-Tensorflow 2.4

As far as I know, Tensorflow model in pb format can be loaded on ML.NET.

However, I'm using a quantization package LPOT (https://github.com/intel/lpot) which utilizes Intel optimized Tensorflow (https://github.com/Intel-tensorflow/tensorflow). Even though Intel-Tensorflow is built on Tensorflow, it uses some Quantized Op which has no registered OpKernel on Tensorflow (e.g. 'QuantizedMatmulWithBiasAndDequantize' is deprecated on TF). As a result, the quantized model cannot be run under native Tensorflow environment without installing Intel-Tensorflow.

My goal is to run this quantized pb Intel-Tensorflow model on ML.NET, does anyone know if Intel-Tensorflow is supported on ML.NET? Or is there any other way to do so?

Any help/suggestion is greatly appreciated.

解决方案

The oneDNN supported in ML.NET depends on the ML.NET integration. If they enable oneDNN in the TensorFlow C++ API, ML.NET could have oneDNN support.

You can try installing stock Tensorflow 2.5 in your ML.NET environment with intel OneDNN enabled. You can install stock Tensorflow wheel from this link: https://pypi.org/project/tensorflow/#files

To install the wheel file: pip install __.whl.

To enable oneDNN optimizations, please set the environment variable TF_ENABLE_ONEDNN_OPTS:

set TF_ENABLE_ONEDNN_OPTS=1

To ensure verbose log is displayed: set DNNL_VERBOSE=1

For more information on oneDNN verbose mode, please refer: https://oneapi-src.github.io/oneDNN/dev_guide_verbose.html

For more information on Intel Optimization for tensorflow, please refer: https://software.intel.com/content/www/us/en/develop/articles/intel-optimization-for-tensorflow-installation-guide.html

这篇关于如何在 ML.NET 上加载和运行 Intel-Tensorflow 模型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！