Commit Graph

439 Commits

Author SHA1 Message Date
Anastasiya Pronina
e70c8e5f0e Ported VAS Object Tracking into OpenCV G-API 2023-12-05 14:58:00 +00:00
Alexander Smorkalov
5df28f1eaa
Merge pull request #24615 from smirnov-alexey:as/infer2_assert_soften
G-API: Soften the argument check in infer2
2023-11-29 17:45:02 +03:00
Anatoliy Talamanov
79797a3eb6
Merge pull request #24584 from TolyaTalamanov:at/implement-inference-only-mode-for-ov-backend
G-API: Implement inference only mode for OV backend #24584

### Changes overview

Introduced `cv::gapi::wip::ov::benchmark_mode{}` compile argument which if enabled force `OpenVINO` backend to run only inference without populating input and copying back output tensors. 

This mode is only relevant for measuring the performance of pure inference without data transfers. Similar approach is using on OpenVINO side in `benchmark_app`: https://github.com/openvinotoolkit/openvino/blob/master/samples/cpp/benchmark_app/benchmark_app.hpp#L134-L139



### Pull Request Readiness Checklist
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
- [ ] 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
2023-11-29 17:40:45 +03:00
Alexey Smirnov
0a862b5295 Soften the 0th argument check in infer2 2023-11-29 12:03:03 +00:00
Anatoliy Talamanov
0e151e3c88
Merge pull request #24060 from TolyaTalamanov:at/advanced-device-selection-onnxrt-directml
G-API: Advanced device selection for ONNX DirectML Execution Provider #24060

### Overview
Extend `cv::gapi::onnx::ep::DirectML` to accept `adapter name` as `ctor` parameter in order to select execution device by `name`.
E.g:
```
pp.cfgAddExecutionProvider(cv::gapi::onnx::ep::DirectML("Intel Graphics"));
```

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-11-16 08:49:53 +03:00
Kumataro
1911c63826
fix: supress GCC13 warnings (#24434)
* fix: supress GCC13 warnings

* fix for review and compile-warning on MacOS
2023-10-26 09:00:58 +03:00
Liutong HAN
a287605c3e Clean up the Universal Intrinsic API. 2023-10-13 19:23:30 +08:00
Alexander Smorkalov
cd7cbe3d41
Merge pull request #24324 from hanliutong:rewrite-fluid
Rewrite Universal Intrinsic code: gapi module (fluid part).
2023-10-13 10:25:07 +03:00
Sean McBride
5fb3869775
Merge pull request #23109 from seanm:misc-warnings
* Fixed clang -Wnewline-eof warnings
* Fixed all trivial clang -Wextra-semi and -Wc++98-compat-extra-semi warnings
* Removed trailing semi from various macros
* Fixed various -Wunused-macros warnings
* Fixed some trivial -Wdocumentation warnings
* Fixed some -Wdocumentation-deprecated-sync warnings
* Fixed incorrect indentation
* Suppressed some clang warnings in 3rd party code
* Fixed QRCodeEncoder::Params documentation.

---------

Co-authored-by: Alexander Smorkalov <alexander.smorkalov@xperience.ai>
2023-10-06 13:33:21 +03:00
Liutong HAN
419060da84 Rewrite fluid related part. 2023-09-22 12:14:43 +08:00
Alexander Smorkalov
748279d5f1
Merge pull request #23904 from kai-waang:removing-unreachable
removing unreachable codes in `gbackend`
2023-09-04 17:06:45 +03:00
Dmitry Matveev
d19fc1264b
Merge pull request #24178 from dmatveev:dm/streaming_queue
G-API: Introduce a Queue Source #24178

- Added a new IStreamSource class: in fact, a wrapper over a concurrent queue;
- Added minimal example on how it can be used;
- Extended IStreamSource with optional "halt" interface to break the blocking calls in the emitter threads when required to stop.
- Introduced a QueueInput class which allows to pass the whole graph's input vector at once. In fact it is a thin wrapper atop of individual Queue Sources.

There is a hidden trap found with our type system as described in https://github.com/orgs/g-api-org/discussions/2

While it works even in this form, it should be addressed somewhere in the 5.0 timeframe.

### Pull Request Readiness Checklist

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
2023-09-04 12:48:53 +03:00
Anatoliy Talamanov
f46f7eff0c
Merge pull request #24059 from TolyaTalamanov:at/add-onnx-cuda-execution-provider
G-API: Support CUDA & TensoRT Execution Providers for ONNXRT Backend #24059

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-08-02 14:13:07 +03:00
Anatoliy Talamanov
a817813b50
Merge pull request #24045 from TolyaTalamanov:at/add-onnx-directml-execution-provider
G-API: Support DirectML Execution Provider for ONNXRT Backend #24045

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-07-26 16:00:20 +03:00
Anatoliy Talamanov
5261961a6e
Merge pull request #24024 from TolyaTalamanov:at/add-onnx-openvino-execution-provider
G-API: Support OpenVINO Execution Provider for ONNXRT Backend #24024

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-07-21 12:18:06 +03:00
Wang Kai
d25d44156b removing unreachable codes in gbackend 2023-07-02 15:33:52 +08:00
Anatoliy Talamanov
b8b8c7c9e5
Merge pull request #23884 from TolyaTalamanov:at/fix-async-infer-ov-backend
G-API: Fix async inference for OpenVINO backend #23884

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-06-28 14:52:15 +03:00
TolyaTalamanov
c0fda696f3 Apply ov::Core WA 2023-06-23 12:16:21 +00:00
Anatoliy Talamanov
60848519b5
Merge pull request #23843 from TolyaTalamanov:at/fix-missing-opaque-kind-for-kernel
G-API: Fix incorrect OpaqueKind for Kernel outputs #23843

### Pull Request Readiness Checklist

#### Overview
The PR is going to fix several problems:
1. Major: `GKernel` doesn't hold `kind` for its outputs. Since `GModelBuilder` traverse graph from outputs to inputs once it reaches any output of the operation it will use its `kind` to create  `Data` meta for all operation outputs. Since it essential for `python` to know `GTypeInfo` (which is `shape` and `kind`) it will be confused.

Consider this operation:
```
 @cv.gapi.op('custom.square_mean', in_types=[cv.GArray.Int], out_types=[cv.GOpaque.Float, cv.GArray.Int])
    class GSquareMean:
        @staticmethod
        def outMeta(desc):
            return cv.empty_gopaque_desc(), cv.empty_array_desc()
```
Even though `GOpaque` is `Float`, corresponding metadata might have `Int` kind because it might be taken from `cv.GArray.Int`
so it will be a problem if one of the outputs of these operation is graph output because python will cast it to the wrong type based on `Data` meta.

2. Minor: Some of the OpenVINO `IR`'s doesn't any layout information for input. It's usually true only for `IRv10` but since `OpenVINO 2.0` need this information to correctly configure resize we need to put default layout if there no such assigned in `ov::Model`. 

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-06-22 12:46:25 +03:00
Anatoliy Talamanov
71790e12ad
Merge pull request #23799 from TolyaTalamanov:at/ov20-backend-implement-missing-kernels
G-API: Implement InferROI, InferList, InferList2 for OpenVINO backend #23799

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-06-20 13:29:23 +03:00
Anatoliy Talamanov
0cf45b89ec
Merge pull request #23796 from TolyaTalamanov:at/align-ie-backend-with-latest-openvino
G-API: Align IE Backend with the latest OpenVINO version #23796

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-06-20 12:33:08 +03:00
Anatoliy Talamanov
b854d4ecd8
Merge pull request #23786 from TolyaTalamanov:at/expose-preprocessing-to-ie-backend
G-API: Expose explicit preprocessing for IE Backend #23786

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-06-14 09:29:49 +03:00
TolyaTalamanov
af95395fe7 Fix ifdef condition 2023-06-07 15:42:54 +01:00
Anatoliy Talamanov
5330112f05
Merge pull request #23595 from TolyaTalamanov:at/implement-openvino-backend
[G-API] Implement OpenVINO 2.0 backend #23595

### Pull Request Readiness Checklist

Implemented basic functionality for `OpenVINO` 2.0 G-API backend.

#### Overview
- [x] Implement `Infer` kernel with some of essential configurable parameters + IR/Blob models format support.
- [ ] Implement the rest of kernels: `InferList`, `InferROI`, `Infer2` + other configurable params (e.g reshape)
- [x] Asyncrhonous execution support
- [ ] Remote context support

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
- [ ] 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
2023-06-02 14:31:03 +03:00
Alexander Smorkalov
2104d61d4a
Merge pull request #23668 from TolyaTalamanov:at/fix-resize-applying-logic-ie-backend
WIP: [G-API] IE Backend: Update the condition for applying the resize preprocessing
2023-06-01 13:55:07 +03:00
Anna Khakimova
6d3dd24622
Merge pull request #21797 from anna-khakimova:ak/merge3_extend_supported_types
GAPI Fluid SIMD:Add support of new several types for the Merge3

- Support of the new several types was added.
- Fixes for the Split/Merge and ConvertTo issues.
2023-05-31 14:59:39 +03:00
Dmitry Matveev
fc5d412ba7
Merge pull request #23597 from dmatveev:dm/gapi_onnx_py_integration
G-API: Integration branch for ONNX & Python-related changes #23597

# Changes overview

## 1. Expose ONNX backend's Normalization and Mean-value parameters in Python

* Since Python G-API bindings rely on `Generic` infer to express Inference, the `Generic` specialization of `onnx::Params` was extended with new methods to control normalization (`/255`) and mean-value; these methods were exposed in the Python bindings
* Found some questionable parts in the existing API which I'd like to review/discuss (see comments)

UPD:
1. Thanks to @TolyaTalamanov normalization inconsistencies have been identified with `squeezenet1.0-9` ONNX model itself; tests using these model were updated to DISABLE normalization and NOT using mean/value.
2. Questionable parts were removed and tests still pass.

### Details (taken from @TolyaTalamanov's comment):

`squeezenet1.0.*onnx` - doesn't require scaling to [0,1] and mean/std because the weights of the first convolution already scaled. ONNX documentation is broken. So the correct approach to use this models is:

1. ONNX: apply preprocessing from the documentation: https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py#L8-L44 but without normalization step:
```
# DON'T DO IT:
# mean_vec = np.array([0.485, 0.456, 0.406])
# stddev_vec = np.array([0.229, 0.224, 0.225])
# norm_img_data = np.zeros(img_data.shape).astype('float32')
# for i in range(img_data.shape[0]):
#     norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i]
#     # add batch channel
#     norm_img_data = norm_img_data.reshape(1, 3, 224, 224).astype('float32')
#     return norm_img_data

# INSTEAD
return img_data.reshape(1, 3, 224, 224)
```

2. G-API: Convert image from BGR to RGB and then pass to `apply` as-is with configuring parameters:
```
net = cv.gapi.onnx.params('squeezenet', model_filename)
net.cfgNormalize('data_0', False)
```
**Note**: Results might be difference because `G-API` doesn't apply central crop but just do resize to model resolution.

---

`squeezenet1.1.*onnx` - requires scaling to [0,1] and mean/std - onnx documentation is correct.
1. ONNX: apply preprocessing from the documentation: https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py#L8-L44
2. G-API: Convert image from BGR to RGB and then pass to `apply` as-is with configuring parameters:
```
net = cv.gapi.onnx.params('squeezenet', model_filename)
net.cfgNormalize('data_0', True) // default
net.cfgMeanStd('data_0', [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
```
**Note**: Results might be difference because `G-API` doesn't apply central crop but just do resize to model resolution.

## 2. Expose Fluid & kernel package-related functionality in Python

* `cv::gapi::combine()`
* `cv::GKernelPackage::size()` (mainly for testing purposes)
* `cv::gapi::imgproc::fluid::kernels()`

Added a test for the above.

## 3. Fixed issues with Python stateful kernel handling

Fixed error message when `outMeta()` of custom python operation fails.

## 4. Fixed various issues in Python tests

1. `test_gapi_streaming.py` - fixed behavior of Desync test to avoid sporadic issues
2. `test_gapi_infer_onnx.py` - fixed model lookup (it was still using the ONNX Zoo layout but was NOT using the proper env var we use to point to one).

### Pull Request Readiness Checklist

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
2023-05-30 17:52:17 +03:00
TolyaTalamanov
dc714c1181 Change logic for applying resize 2023-05-24 13:06:19 +00:00
Dmitry Matveev
1d02146810 Bump supported ONNX RT version to 1.14.1
- Existing tests pass with the ONNX models mentioned in tests.
2023-04-22 20:15:40 +00:00
TolyaTalamanov
66abbf4122 Compilation fix 2023-04-11 10:33:42 +00:00
TolyaTalamanov
0f984ea0f0 Handle const inputs descs in giebackend 2023-04-11 10:25:52 +00:00
TolyaTalamanov
8a95f4f0e6 Handle meta for multiple infer inputs 2023-04-10 09:54:26 +00:00
Alexander Alekhin
3f7ec99166 build: eliminate build warnings on Ubuntu 20.04/16.04 2022-12-20 06:46:30 +00:00
Alexander Alekhin
91998d6424
Merge pull request #22935 from alalek:gapi_error
G-API: replace GAPI_Assert() with 'false' and '0' to GAPI_Error()

* gapi: GAPI_Error() macro

* gapi: replace GAPI_Assert() with 'false' and '0' to GAPI_Error()

* build: eliminate 'unreachable code' after CV_Error() (MSVC 2015)

* build: eliminate 'unreachable code' warning for MSVS 2015/2017

- observed in constructors stubs with throwing exception
2022-12-19 06:05:15 +00:00
Alexander Alekhin
be326ff752 build: fix/eliminate MSVC warnings 2022-12-10 12:19:31 +00:00
Alexey Smirnov
4c74e6d89d Copy mpashchenkov's changes
Minor refactoring

Partially address review comments

Move DX-related stuff from the sample to a default source

Simplify the default OneVPL config

Address minor review comments

Add class for the default VPL source

WIP: Add initial stub for tests with description

Removing default vpl source and minor refactoring

Refactor default files

Fix build and application crash

Address review comments

Add test on VPL + OCL interaction compared to CPU behavior

Fix test
2022-11-16 14:17:02 +01:00
Anatoliy Talamanov
2aad039b4f
Merge pull request #22494 from TolyaTalamanov:at/expose-all-core-to-python
G-API Expose all core operations to python

* Expose all G-API core operations to python

* Fix typo in python gapi types test
2022-11-08 11:43:38 +00:00
Alexander Smorkalov
bf5d7c0c10
Merge pull request #22588 from TolyaTalamanov:at/sync-ie-request-pool
G-API: Add synchronous execution for IE backend
2022-10-04 11:32:21 +03:00
Alexander Smorkalov
fef8d4c990
Merge pull request #22017 from xiong-jie-y:py_onnx
Add python bindings for G-API onnx
2022-10-04 10:33:10 +03:00
TolyaTalamanov
9fd877acc9 Merge branch '4.x' of github.com:opencv/opencv into at/sync-ie-request-pool 2022-10-04 06:48:28 +00:00
TolyaTalamanov
aafb7567c1 Add tests 2022-10-03 10:58:21 +00:00
TolyaTalamanov
cf5db9b94f Add handle to configure async/sync infer mode 2022-10-03 09:43:50 +00:00
TolyaTalamanov
589b6c15f0 Fix windows warning 2022-10-03 09:43:50 +00:00
TolyaTalamanov
2af0813634 Add sync/async executors for infer request 2022-10-03 09:43:50 +00:00
TolyaTalamanov
15d2a5faf8 Add sync infer request 2022-10-03 09:43:50 +00:00
TolyaTalamanov
a6fbd8287c Fix comments to review 2022-10-03 08:04:31 +00:00
TolyaTalamanov
b0b77b3047 Add cfgOutputPrecision 2022-10-03 08:04:31 +00:00
Biswapriyo Nath
6cf0910842
Merge pull request #22462 from Biswa96:fix-directx-check
* cmake: Fix DirectX detection in mingw

The pragma comment directive is valid for MSVC only. So, the DirectX detection
fails in mingw. The failure is fixed by adding the required linking library
(here d3d11) in the try_compile() function in OpenCVDetectDirectX.cmake file.
Also add a message if the first DirectX check fails.

* gapi: Fix compilation with mingw

These changes remove MSVC specific pragma directive. The compilation fails at
linking time due to absence of proper linking library. The required libraries
are added in corresponding CMakeLists.txt file.

* samples: Fix compilation with mingw

These changes remove MSVC specific pragma directive. The compilation fails at
linking time due to absence of proper linking library. The required libraries
are added in corresponding CMakeLists.txt file.
2022-10-03 08:37:36 +03:00
TolyaTalamanov
5ea912e778 Change warning message 2022-09-13 08:28:34 +01:00
TolyaTalamanov
bcc19a622d Replace MFX major version assertion to warning 2022-09-12 17:54:00 +01:00