a3fae37fe1
* Dynamic conv first commit * Fixes after rebase * Refactoring: 1. Conv node code refactor 2. DW conv fusing is disabled for dynamic case 3. Weights static shape constraint was added * Minor fix for 1st rank bias * WA fix * MKLDNN dynamic conv fixes * Temporal WA on format serialization * Convolution SL prepared for dynamism * Fix for bias fusing * Update for nspc heuristics * Convolution SL tests are updated with dynamic shapes * GroupConv SL tests are updated with dynamic shapes * Wip * Dynamic shapes post ops support * Dynamic shapes convolution full SL tests support * Convolution builder changed to support pShape * Convolution CPU SL test moved to the new Test Infra * Skip tests conf update * Auto padding support in dynamic mode with test * Convolution dyn tests for bf16 * Group Conv test commented * Submodule up * First review fixes * Group convolution dynamic shapes SL test * Serialize format method has been fixed * Floating point numbers resolution changed to even number * AutoPad flag was added * Skip test config updated with changed signature * An attempt to reduce SL test time * Dilated convolution tests extracted from the precommit |
||
|---|---|---|
| .ci | ||
| .github | ||
| cmake | ||
| docs | ||
| inference-engine | ||
| licensing | ||
| model-optimizer | ||
| ngraph | ||
| openvino | ||
| runtime | ||
| samples | ||
| scripts | ||
| tests | ||
| thirdparty | ||
| tools | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| CMakeLists.txt | ||
| CODEOWNERS | ||
| install_build_dependencies.sh | ||
| Jenkinsfile | ||
| LICENSE | ||
| README.md | ||
| SECURITY.md | ||
OpenVINO™ Toolkit
This toolkit allows developers to deploy pre-trained deep learning models through a high-level C++ Inference Engine API integrated with application logic.
This open source version includes several components: namely Model Optimizer, nGraph and Inference Engine, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. It supports pre-trained models from the Open Model Zoo, along with 100+ open source and public models in popular formats such as Caffe*, TensorFlow*, MXNet* and ONNX*.
Repository components:
License
Deep Learning Deployment Toolkit is licensed under Apache License Version 2.0. By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.
Resources:
- Docs: https://docs.openvinotoolkit.org/
- Wiki: https://github.com/openvinotoolkit/openvino/wiki
- Issue tracking: https://github.com/openvinotoolkit/openvino/issues
- Storage: https://storage.openvinotoolkit.org/
- Additional OpenVINO™ modules: https://github.com/openvinotoolkit/openvino_contrib
- Intel® Distribution of OpenVINO™ toolkit Product Page
- Intel® Distribution of OpenVINO™ toolkit Release Notes
Support
Please report questions, issues and suggestions using:
- The
openvinotag on StackOverflow* - GitHub* Issues
- Forum
* Other names and brands may be claimed as the property of others.