OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Go to file
Konrad Dobros d3ea03bbfc
[IE CLDNN] Enable int8 activation for fsv16 format (#516)
This change enables int8/uint8 standalone activation to use optimized
block format (b_fs_yx_fsv16). This should eliminate cases where such
activation had reorders before and after.

Support for this is already provided by activation_kernel_ref implementation.

Related JIRA: CVS-28494
2020-05-27 05:37:38 +03:00
.github/workflows Fix MO CI job name (#520) 2020-05-23 00:24:05 +03:00
cmake Fixed compilation with clang-10 + xcode (#521) 2020-05-26 17:17:36 +03:00
docs add plugin template (#515) 2020-05-22 22:34:00 +03:00
inference-engine [IE CLDNN] Enable int8 activation for fsv16 format (#516) 2020-05-27 05:37:38 +03:00
model-optimizer [ MO ONNX ] TopK-1/10/11 proper extracting (#600) 2020-05-26 21:53:24 +03:00
ngraph Change Elu a regular op since decomposition works extremely slowly (#582) 2020-05-26 21:59:08 +03:00
scripts publish master branch snapshot, revision 49482ae3bea0cbaa07474f86f36db11943142687 2020-05-13 21:12:22 +03:00
tests [Stress] Updated test_configs with new path to OMZ mtcnn models (#602) 2020-05-26 20:11:46 +03:00
tools publish master branch snapshot, revision 49482ae3bea0cbaa07474f86f36db11943142687 2020-05-13 21:12:22 +03:00
.gitattributes Publishing R3 2018-10-16 13:45:03 +03:00
.gitignore publish master branch snapshot, revision 8d31237e2c3f673cbb0f0ba110fc10f5cce1d2bb 2020-05-22 02:23:12 +03:00
.gitmodules add submodules for mkl-dnn, gflags and gtest 2020-05-21 23:00:55 +03:00
azure-pipelines.yml Use compute optimized VMs for CI (#567) 2020-05-25 21:31:57 +03:00
build-instruction.md publish master branch snapshot, revision 59af1853ca21ea08acf17b177da0b239753deb46 2020-05-18 17:21:58 +03:00
CMakeLists.txt Fixed compilation with clang-10 + xcode (#521) 2020-05-26 17:17:36 +03:00
CODEOWNERS CODEOWNERS: added cpu/gpu developers teams (#540) 2020-05-25 21:54:54 +03:00
CONTRIBUTING.md Create CONTRIBUTING.md 2020-05-19 19:04:27 +03:00
get-started-linux.md Publishing 2020.1 content 2020-02-11 22:48:49 +03:00
install_dependencies.sh Publishing 2020.1 content 2020-02-11 22:48:49 +03:00
Jenkinsfile publish master branch snapshot, revision cdcab9d7ab48ffb0ee5629fabbfa06cb45debd9b 2020-04-15 19:01:57 +03:00
LICENSE Publishing R3 2018-10-16 13:45:03 +03:00
README.md fixed latest release 2020-05-21 17:27:44 +03:00

OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository

Stable release Apache License Version 2.0

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 two components: namely Model Optimizer and Inference Engine, as well as CPU, GPU 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.

Documentation

How to Contribute

See CONTRIBUTING for details. Thank you!

Support

Please report questions, issues and suggestions using:


* Other names and brands may be claimed as the property of others.