openvino/tools
Bonhun Koo 572d00eaa2
[POT][GNA] add mixed-precision support for Accuracy Aware Quantization (#12470)
* [POT] add GNA3 mode

* [POT][GNA3] add mixed-precision support for Accuracy Aware Quantization

* [POT] add GNA AAQ sanity test with synthetic data

* [POT][GNA3] add GNA3.5 mode and minimize AAQ option

* [POT] fix pot/ci fails on config test
2022-09-20 08:47:33 +09:00
..
benchmark_tool [BENCHMARK APP/PYTHON] Fix a bug causing nstreams parameter to behave differently across Python and C++ benchmark_app (#12935) 2022-09-14 09:53:26 +02:00
compile_tool Arm cross compilation (#12807) 2022-08-30 22:23:14 +04:00
cross_check_tool [MO, POT] Top up upper bounds for TensorFlow and NumPy modules in all requirement files (#12191) 2022-08-03 16:18:41 +04:00
deployment_manager DOCS: ported changes from 2022.1 release branch (#11206) 2022-03-24 22:27:29 +03:00
legacy/benchmark_app Arm cross compilation (#12807) 2022-08-30 22:23:14 +04:00
mo LTO for frontends and python (#12890) 2022-09-05 08:10:11 +04:00
openvino_dev Ability to build against oneTBB build RelWithDebInfo (#12940) 2022-09-07 09:58:30 +04:00
pot [POT][GNA] add mixed-precision support for Accuracy Aware Quantization (#12470) 2022-09-20 08:47:33 +09:00
.gitignore Align folder structure for Benchmark Tool (#6625) 2021-07-19 11:57:51 +03:00
CMakeLists.txt simple Windows installer POC (#12308) 2022-07-27 14:04:22 +04:00
README.md fix errors in documentation (#9384) 2022-01-27 19:39:49 +03:00
requirements_dev.in Add ability to generate requirements.txt files with dev tags (#9986) 2022-01-28 18:23:10 +03:00

README.md

OpenVINO™ Python* development tools

General

OpenVINO includes following tools:

  • openvino.tools.benchmark

Please, refer to https://docs.openvino.ai for details.

Installation

Prerequisites

Install prerequisites first:

1. Python

Install Python prerequisites:

Run following command to install these prerequisites on Ubuntu*:

sudo apt-get install python3 python3-dev python3-setuptools python3-pip

Python setuptools and python package manager (pip) install packages into system directory by default. There are several options:

  • work inside [virtual environment][virtualenv] (best solution).
  • use --user option for all pip commands.
  • install all dependencies with sudo permissions.

In order to use virtual environment you should install it:

python3 -m pip install virtualenv
python3 -m virtualenv -p `which python3` <directory_for_environment>

Before starting to work inside virtual environment, it should be activated:

source <directory_for_environment>/bin/activate

Virtual environment can be deactivated using command

deactivate

2. Install packages

You can install tools by specifying path to tool with setup.py in pip install command:

python3 -m pip install <tools_folder>/

For example, to install Benchmark Tool, use the following command:

python3 -m pip install benchmark_tool/

Configuration

Each subpackage has specific configuration. Please, refer to specific subpackage documentation for details.