IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Install guides improvements (#6418)

Browse Source 
* Install guides improvements

* add bullet to conda  System Requirements

* fix formating

* - Add conda install command for Ubuntu20

- fix typo /tmp

* added conda prerequisites

* Update installing-openvino-apt.md

* Update installing-openvino-conda.md

* Update installing-openvino-conda.md

CentOS 7.6

* Update installing-openvino-apt.md

APT Repository

* Update installing-openvino-conda.md

Added Introduction & notice about runtime package

* Update installing-openvino-conda.md

Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com>
This commit is contained in:
Sergey Lyubimtsev 2021-07-14 17:55:12 +03:00 committed by GitHub
parent 34c20ad9a8
commit c8c515e403
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 112 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
docs/install_guides/installing-openvino-apt.md
View File

@ -4,7 +4,16 @@ This guide provides installation steps for Intel® Distribution of OpenVINO™ t
> **IMPORTANT**: By downloading and using this container and the included software, you agree to the terms and conditions of the [software license agreements](https://software.intel.com/content/dam/develop/external/us/en/documents/intel-openvino-license-agreements.pdf). Please, review the content inside the `<openvino_install_root>/licensing` folder for more details.
> **NOTE**: Intel® Graphics Compute Runtime for OpenCL™ is not a part of OpenVINO™ APT distribution. You can install it from the [Intel® Graphics Compute Runtime for OpenCL™ GitHub repo](https://github.com/intel/compute-runtime).
> **NOTE**: Intel® Graphics Compute Runtime for OpenCL™ is not a part of OpenVINO™ APT distribution. You can install it from the [Intel® Graphics Compute Runtime for OpenCL™ GitHub repo](https://github.com/intel/compute-runtime).
## System Requirements
The complete list of supported hardware is available in the [Release Notes](https://software.intel.com/content/www/us/en/develop/articles/openvino-relnotes.html#inpage-nav-8).
**Operating Systems**
- Ubuntu 18.04.x long-term support (LTS), 64-bit
- Ubuntu 20.04.0 long-term support (LTS), 64-bit
## Included with Runtime Package
@ -31,50 +40,46 @@ The following components are installed with the OpenVINO developer package:
| [Documentation for Pre-Trained Models ](@ref omz_models_group_intel) | Documentation for the pre-trained models available in the [Open Model Zoo repo](https://github.com/openvinotoolkit/open_model_zoo). |
| Deep Learning Streamer (DL Streamer) | Streaming analytics framework, based on GStreamer\*, for constructing graphs of media analytics components. For the DL Streamer documentation, see [DL Streamer Samples](@ref gst_samples_README), [API Reference](https://openvinotoolkit.github.io/dlstreamer_gst/), [Elements](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/Elements), [Tutorial](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/DL-Streamer-Tutorial). |
## Set up the Repository
### Install the GPG key for the repository
## Install Packages
### Set up the OpenVINO™ Toolkit APT Repository
#### Install the GPG key for the Repository
1. Download the public key from [https://apt.repos.intel.com/openvino/2021/GPG-PUB-KEY-INTEL-OPENVINO-2021](https://apt.repos.intel.com/openvino/2021/GPG-PUB-KEY-INTEL-OPENVINO-2021) and save it to a file.
2. Add this key to the system keyring:
```sh
sudo apt-key add <PATH_TO_DOWNLOADED_GPG_KEY>
```
> **NOTE**: You might need to install GnuPG: `sudo apt-get install gnupg`
3. Check the list of APT keys running the following command:
```sh
sudo apt-key list
```
### Add the APT Repository
#### Add the Repository
Run the following command:
```sh
echo "deb https://apt.repos.intel.com/openvino/2021 all main" | sudo tee /etc/apt/sources.list.d/intel-openvino-2021.list
```
### Update the list of packages
#### Update the List of Packages
Run the `update` command:
```sh
sudo apt update
```
There are full release Runtime and Developer packages, and also some available components.
**Runtime Packages**
- Ubuntu 18.04: `intel-openvino-runtime-ubuntu18`
- Ubuntu 20.04: `intel-openvino-runtime-ubuntu20`
**Developer Packages**
- Ubuntu 18.04: `intel-openvino-dev-ubuntu18`
- Ubuntu 20.04: `intel-openvino-dev-ubuntu20`
### Get the list of available packages
#### Verify that the APT Repository is Properly Set Up
Run the `apt-cache` command to see a list of all available OpenVINO packages and components:
```sh
apt-cache search openvino
```
#### Examples
See the example commands below:
* **Runtime Packages**
@ -97,29 +102,23 @@ apt-cache search openvino
sudo apt-cache search intel-openvino-dev-ubuntu20
```
## Install the runtime or developer packages using the APT Package Manager
Intel® OpenVINO will be installed in: `/opt/intel/openvino_<VERSION>.<UPDATE>.<BUILD_NUM>`
### Install Runtime or Developer Packages using the APT Package Manager
Intel® OpenVINO™ Toolkit will be installed in: `/opt/intel/openvino_<VERSION>.<UPDATE>.<BUILD_NUM>`
A symlink will be created: `/opt/intel/openvino_<VERSION>`
---
### To Install a specific version
To get a list of OpenVINO packages available for installation:
#### To Install a Specific Version
1. Get a list of OpenVINO packages available for installation:
```sh
sudo apt-cache search intel-openvino-runtime-ubuntu18
```
To install a specific version of an OpenVINO package:
2. Install a specific version of an OpenVINO package:
```sh
sudo apt install intel-openvino-<PACKAGE_TYPE>-ubuntu<OS_VERSION>-<VERSION>.<UPDATE>.<BUILD_NUM>
```
#### Examples
* **Runtime Package**
See the example commands below:
* **Runtime Package**<br>
On Ubuntu 18.04:
```sh
sudo apt install intel-openvino-runtime-ubuntu18-2021.1.105
@ -138,10 +137,17 @@ sudo apt install intel-openvino-<PACKAGE_TYPE>-ubuntu<OS_VERSION>-<VERSION>.<UPD
sudo apt install intel-openvino-dev-ubuntu20-2021.1.105
```
---
### To Uninstall a specific version
#### To check for Installed Packages and Versions
To uninstall a specific full runtime package:
To get a list of installed OpenVINO packages:
```sh
apt list --installed | grep openvino
```
#### To Uninstall a Specific Version
To uninstall a specific package:
```sh
sudo apt autoremove intel-openvino-<PACKAGE_TYPE>-ubuntu<OS_VERSION>-<VERSION>.<UPDATE>.<BUILD_NUM>
```

59
docs/install_guides/installing-openvino-conda.md
View File

@ -2,22 +2,39 @@
This guide provides installation steps for Intel® Distribution of OpenVINO™ toolkit distributed through the Anaconda* Cloud.
> **NOTE**: Only runtime packages are available from Anaconda* Cloud.
## Introduction
OpenVINO™ toolkit is a comprehensive toolkit for quickly developing applications and solutions that solve a variety of tasks including emulation of human vision, automatic speech recognition, natural language processing, recommendation systems, and many others. Based on latest generations of artificial neural networks, including Convolutional Neural Networks (CNNs), recurrent and attention-based networks, the toolkit extends computer vision and non-vision workloads across Intel® hardware, maximizing performance. It accelerates applications with high-performance, AI and deep learning inference deployed from edge to cloud.
The Intel® Distribution of OpenVINO™ toolkit\*:
- Enables CNN-based deep learning inference on the edge
- Supports heterogeneous execution across Intel® CPU, Intel® Integrated Graphics, Intel® Neural Compute Stick 2, and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs
- Speeds time-to-market via an easy-to-use library of computer vision functions and pre-optimized kernels
The **runtime package** includes the following components installed by default:
| Component | Description |
|-----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications. |
## System Requirements
**Software**
- [Anaconda* distribution](https://www.anaconda.com/products/individual/)
**Operating Systems**
- Ubuntu* 18.04 long-term support (LTS), 64-bit
- CentOS* 7.6, 64-bit
- macOS* 10.14.x versions.
- Windows 10*, 64-bit Pro, Enterprise or Education (1607 Anniversary Update, Build 14393 or higher) editions
- Windows Server* 2016 or higher
| Supported Operating System | [Python* Version (64-bit)](https://www.python.org/) |
| :------------------------------------------------------------| :---------------------------------------------------|
| Ubuntu* 18.04 long-term support (LTS), 64-bit | 3.6, 3.7 |
| Ubuntu* 20.04 long-term support (LTS), 64-bit | 3.6, 3.7 |
| CentOS* 7.6, 64-bit | 3.6, 3.7 |
| macOS* 10.15.x | 3.6, 3.7 |
| Windows 10*, 64-bit | 3.6, 3.7 |
## Install the runtime package using the Anaconda* Package Manager
## Install the Runtime Package using the Anaconda* Package Manager
1. Set up the Anaconda* environment: 
```sh
@ -26,11 +43,19 @@ This guide provides installation steps for Intel® Distribution of OpenVINO™ t
```sh
conda activate py37
```
2. Updated conda to the latest version:
2. Update Anaconda environment to the latest version:
```sh
conda update --all
```
3. Install the Intel® Distribution of OpenVINO™ Toolkit:
3. Install pre-requisites:
```sh
conda install numpy
```
4. Install the Intel® Distribution of OpenVINO™ Toolkit:
- Ubuntu* 20.04
```sh
conda install openvino-ie4py-ubuntu20 -c intel
```
- Ubuntu* 18.04
```sh
conda install openvino-ie4py-ubuntu18 -c intel
@ -43,19 +68,13 @@ This guide provides installation steps for Intel® Distribution of OpenVINO™ t
```sh
conda install openvino-ie4py -c intel
```
4. Verify the package installed:
5. Verify the package is installed:
```sh
python -c "import openvino"
python -c "from openvino.inference_engine import IECore"
```
Now you can start to develop and run your application.
## Known Issues and Limitations
- You cannot use Python bindings included in Intel® Distribution of OpenVINO™ toolkit with [Anaconda* distribution](https://www.anaconda.com/products/individual/)
- You cannot use Python OpenVINO™ bindings included in Anaconda* package with official [Python distribution](https://www.python.org/).
If installation was successful, you will not see any error messages (no console output).
Now you can start developing your application.
## Additional Resources

45
docs/install_guides/installing-openvino-yum.md
View File

@ -8,6 +8,14 @@ This guide provides installation steps for the Intel® Distribution of OpenVINO
> **NOTE**: Only runtime packages are available via the YUM repository.
## System Requirements
The complete list of supported hardware is available in the [Release Notes](https://software.intel.com/content/www/us/en/develop/articles/openvino-relnotes.html#inpage-nav-8).
**Operating Systems**
- CentOS 7.6, 64-bit
## Included with Runtime Package
The following components are installed with the OpenVINO runtime package:
@ -18,6 +26,8 @@ The following components are installed with the OpenVINO runtime package:
| [OpenCV*](https://docs.opencv.org/master/) | OpenCV* community version compiled for Intel® hardware. |
| Deep Learning Stream (DL Streamer) | Streaming analytics framework, based on GStreamer, for constructing graphs of media analytics components. For the DL Streamer documentation, see [DL Streamer Samples](@ref gst_samples_README), [API Reference](https://openvinotoolkit.github.io/dlstreamer_gst/), [Elements](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/Elements), [Tutorial](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/DL-Streamer-Tutorial). |
## Install Packages
## Set up the Repository
> **NOTE:** You must be logged in as root to set up and install the repository.
@ -39,25 +49,23 @@ Configure YUM with the OpenVINO repository to install OpenVINO. You have two opt
```
* **OPTION 2:** Create the repository file manually:
1. Navigate to the repository directory:
```sh
cd /etc/yum.repos.d
```
2. Edit the repo file:
```sh
vi intel-openvino-2021.repo
```
3. Append the following code:
1. Create the YUM repo file in the /tmp directory as a normal user:
```sh
tee > /tmp/openvino-2021.repo << EOF
[intel-openvino-2021]
name=Intel(R) Distribution of OpenVINO 2021
baseurl=https://yum.repos.intel.com/openvino/2021
enabled=1
gpgcheck=1
gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-INTEL-OPENVINO-2021
EOF
```
4. Save and close the `intel-openvino-2021.repo` file.
5. Import the gpg public key for the repository:
2. Move the newly created openvino-2021.repo file to the YUM configuration directory /etc/yum.repos.d:
```sh
sudo mv /tmp/openvino-2021.repo /etc/yum.repos.d
```
3. Import the gpg public key for the repository:
```sh
sudo rpm --import https://yum.repos.intel.com/openvino/2021/setup/RPM-GPG-KEY-INTEL-OPENVINO-2021
```
@ -103,6 +111,21 @@ To install the full runtime version of the OpenVINO package:
sudo yum install intel-openvino-runtime-centos7-<VERSION>.<UPDATE>.<BUILD_NUM>
```
#### Examples
```sh
sudo yum install intel-openvino-runtime-centos7-2021.3.394
```
---
### To check for installed packages and version
To check a specific version of an OpenVINO package:
```sh
yum list installed intel-openvino*
```
---
### To Uninstall a specific version