OpenVINO backend for INT8 models #23987
### Pull Request Readiness Checklist
TODO:
- [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069)
- [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum)
- [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039)
- [x] Single layer tests (convolution)
- [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~
Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`:
| backend | performance (median time) |
|---|---|
| OpenCV | 77.42ms |
| OpenVINO 2023.0 | 10.90ms |
CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz`
Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef
---
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Use ngraph::Output in OpenVINO backend wrapper #24196
### Pull Request Readiness Checklist
resolves https://github.com/opencv/opencv/issues/24102
* Use `ngraph::Output<ngraph::Node>>` insead of `std::shared_ptr<ngraph::Node>` as a backend wrapper. It lets access to multi-output nodes: 588ddf1b18/modules/dnn/src/net_openvino.cpp (L501-L504)
* All layers can be customizable with OpenVINO >= 2022.1. nGraph reference code used for default layer implementation does not required CPU plugin also (might be tested by commenting CPU plugin at `/opt/intel/openvino/runtime/lib/intel64/plugins.xml`).
* Correct inference if only intermediate blobs requested.
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Remove legacy nGraph logic #24072
### Pull Request Readiness Checklist
TODO:
- [x] Test with OpenVINO 2021.4 (tested locally)
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Switch to new OpenVINO API after 2022.1 release
* Pass Layer_Test_Convolution_DLDT.Accuracy/0 test
* Pass test Test_Caffe_layers.Softmax
* Failed 136 tests
* Fix Concat. Failed 120 tests
* Custom nGraph ops. 19 failed tests
* Set and get properties from Core
* Read model from buffer
* Change MaxPooling layer output names. Restore reshape
* Cosmetic changes
* Cosmetic changes
* Override getOutputsInfo
* Fixes for OpenVINO < 2022.1
* Async inference for 2021.4 and less
* Compile model with config
* Fix serialize for 2022.1
* Asynchronous inference with 2022.1
* Handle 1d outputs
* Work with model with dynamic output shape
* Fixes with 1d output for old API
* Control outputs by nGraph function for all OpenVINO versions
* Refer inputs in PrePostProcessor by indices
* Fix cycled dependency between InfEngineNgraphNode and InfEngineNgraphNet.
Add InferRequest callback only for async inference. Do not capture InferRequest object.
* Fix tests thresholds
* Fix HETERO:GPU,CPU plugin issues with unsupported layer
Add lightweight IE hardware targets checks
nGraph: Concat with paddings
Enable more nGraph tests
Restore FP32->FP16 for GPU plugin of IE
try to fix buildbot
Use lightweight IE targets check only starts from R4
Dmitry Kurtaev
Oleg Pipikin
Alexander Alekhin
Alexander Alekhin
Ilya Churaev
Liubov Batanina
Omar Alzaibaq
Maksim Doronin
Ilya Churaev
Dmitry Kurtaev
Ilya Lavrenov
Alexander Alekhin
Brian Wignall