Comments (6)
👍
from open_model_zoo.
Hi @RachelRen05 ,
How do you use Inference Engine binaries to build the demos? Are you using openVINO R3 binary package and source environment script from there?
from open_model_zoo.
Hi @vmatveic,
I used the following command to build the demos using Inference Engine:
cmake -DCMAKE_BUILD_TYPE=Release /home/<hostname>/code/dldt/inference-engine
I didn't use OpenVINO binary package, I used OpenVINO open source code.
You can refer to: https://software.intel.com/en-us/forums/computer-vision/topic/798642
from open_model_zoo.
Hi @RachelRen05 ,
Let me comment regarding proper way of working with Open Source version of the product:
- There is open-model-zoo repo with a list of demos. These demos are designed to be built separately with the IE environment source before. If you want to build these demos then you need to have OpenVINO package (of appropriate version, currently for R3) installed (can be taken from https://software.intel.com/en-us/openvino-toolkit). Then you need to source an environment from that package (to get InferenceEngine and OpenCV configured for CMake). After that you are able to successfully build demos by creating of own folder and running of “cmake ..” command from here.
- There is another dldt repo which is used to contribute to InferenceEngine core part. If you want to build dldt sources then you can do that like you did (clone dldt repo and build it). Also, it’s implied that the samples from this repo are built together with this dldt project but not separately. If you still want to build these samples separately then you need to copy samples to own location and update its CMake architecture manually + copy extensions here (to have it similar to demos structure within open-model-zoo) and use an environment from an OpenVINO binary package.
- Also, there is still a possibility to use built dldt binaries like openVINO environment for a separate samples/demos build. You need to set InferenceEngine_DIR to a cmake folder you run “cmake -DGEMM=MKL -DENABLE_MKL_DNN=ON -DCMAKE_BUILD_TYPE=Release ..” command from. But please note, in R3 release this possibility is not completely verified but it will be improved in R4 (also, in R4 you will not need to copy extensions to samples/demos directory, it will be automatically used from binaries).
So, just to repeat, we suggest to use openVINO package (of R version currently) for a separate demos build and use an environment from here. R3 – because current GitHub version of the open source project is adapted to R3 version of openVINO.
Thanks!
from open_model_zoo.
Is this still relevant or we can close?
from open_model_zoo.
Please, reopen if still relevant
from open_model_zoo.
Related Issues (20)
- G-API Gaze Estimation demo lists `m_es` parameter as optional but fails to run when it is not set HOT 1
- [Feature Request]: Gaze Estimation Demos questions HOT 2
- Issue running sound classification demo HOT 9
- Benchmark data in Intel Xe Graphic and Arc Graphic for Single Image Super Resolution Model HOT 1
- unable to download MS-ASL-100 dataset HOT 1
- How to let OpenVino recoginze Intel Agilex® 7 Device HOT 11
- Converting model error with wav2vec2-base
- Linked to Pre Trained Weights Broken? HOT 1
- Use batch size larger than 1 in models with dynamic output HOT 3
- OpenVino development tools not getting installed, throwing , No module named 'distutils'. HOT 1
- omz_downloader command not found HOT 3
- Human Pose estimation-001 model input size mismatch HOT 5
- GT File Generation For Multi-Camera Multi-Target Tracking HOT 1
- ModuleNotFoundError: No module named 'openvino.model_zoo' HOT 3
- background_subtraction_demo cpp cannot build HOT 2
- Documentation for the gaze estimation model HOT 2
- Failed to build omz-tools HOT 1
- Failed to run background_subtraction_demo_gapi with Media Files Available for Demos
- Can't import 'model_zoo' package after PR 3907
- Can't run object_detection_demo.py with GPU or CPU. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from open_model_zoo.