Commit Graph

792 Commits

Author SHA1 Message Date
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
Alexander Alekhin
1656e7573e gapi: fix static build with openvino 2023-06-21 14:17:44 +00:00
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
Anatoliy Talamanov
a371bdac9d
Merge pull request #23766 from TolyaTalamanov:at/segmentation-demo-desync
G-API: Refine Semantic Segmentation Demo #23766

### Overview
* Supported demo working with camera id (e.g `--input=0`)
* Supported 3d output segmentation models (e.g `deeplabv3`)
* Supported `desync` execution
* Supported higher camera resolution
* Changed the color map to pascal voc (https://cloud.githubusercontent.com/assets/4503207/17803328/1006ca80-65f6-11e6-9ff6-36b7ef5b9ac6.png)

### 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
2023-06-13 18:06:19 +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
Dmitry Matveev
3871984028 G-API: Fix compilation error in Standalone mode
- Point3f was added to type traits but was missing in the "own" package; fixed.
2023-04-02 17:52:53 +03:00
Alexander Smorkalov
b56a52c49b
Merge pull request #22471 from anna-khakimova:ak/fix_resize4lpi_tests
Increasing tolerance for Preproc4lpiTest set on ARM
2023-03-24 15:31:48 +03:00
Anna Khakimova
0bb84096a2 Fix tolerance for Preproc4lpiTest set 2023-03-24 14:20:22 +03:00
Anatoliy Talamanov
6c235c8edb
Merge pull request #23211 from TolyaTalamanov:at/pipeline-modeling-tool-perf-alignment
[G-API] Pipeline modeling tool: Refactor calculating performance statistics

* Add warmup execution

* Align perf metrics

* Add busy wait mode for source

* Small fix for late frames

* pl_fn to src_fn

* Change show statistics

* Correct warm-up iteration

* Properly calculate drop frames

* Enable frame dropping for streaming mode

* Enable frame dropping for streaming mode

* Fix comments to review

* Fix typos

* Cosmetic
2023-02-15 14:04:14 +03:00
Maksim Shabunin
e4acd74e87 Fix some clang 14 warnings 2023-02-07 01:19:00 +03:00
Alexander Smorkalov
c855dcc52f Supressed tones of Wdeprecated-copy that jump out of GTes after XCode update to 13.1 on Mac M1. 2023-02-02 13:54:47 +03:00
Maksim Shabunin
c1e5c16ff3 Backport C-API cleanup (imgproc) from 5.x 2023-01-16 23:29:50 +03:00
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
Maksim Shabunin
e93d976d00 gapi: fix InferWithReshape test crash when data is not found 2022-11-19 01:56:45 +03:00
Anatoliy Talamanov
64aad34cb4
Merge pull request #22735 from TolyaTalamanov:at/expose-all-imgproc-to-python
G-API Expose all imgproc operations to python

* Expose imgproc operations

* Fix alignment
2022-11-18 15:25:51 +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
JopKnoppers
0b5fd4f6bb
Included thread in gapi_async_test.cpp
Preventing: gapi_async_test.cpp:448:26: error: ‘sleep_for’ is not a member of ‘std::this_thread’
2022-10-31 12:19:04 +01:00
Dmitry Matveev
b619477be9 Fix issues with VA_INCLUDE_HEADERS when building with CUDA support
...and not only?
2022-10-28 04:02:35 +00:00
TolyaTalamanov
5f50e7bafe Criteria -> Criterion 2022-10-06 09:41:30 +00:00
TolyaTalamanov
839321642e Move impl from class 2022-10-05 12:01:45 +00:00
TolyaTalamanov
9f88a65873 Fix functional pipeline tool tests 2022-10-04 14:23:05 +00:00
TolyaTalamanov
1113c9ab10 Support num_iters criteria for pipeline tool 2022-10-04 08:37:56 +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
5a0c85b3ef Refactor tests 2022-10-04 07:05:40 +00:00
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
Alexander Smorkalov
7208f63221
Merge pull request #22583 from TolyaTalamanov:at/add-cfg-output-precision-for-ie-backend
G-API: API for configuring model output precision for IE backend
2022-10-03 15:54:00 +03:00
TolyaTalamanov
0cd4396180 Expand modeling tool to support infer_mode 2022-10-03 11:08:15 +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
b1d28d5b4a Expand performance report 2022-10-03 09:04:49 +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
Alexander Smorkalov
3a64607d94
Merge pull request #22518 from TolyaTalamanov:at/expand-modeling-tool-to-support-config-in-yml
[G-API] Pipeline modeling tool - support local infer node config
2022-09-27 14:24:35 +03:00
TolyaTalamanov
4521d66103 Remove r-value ref 2022-09-26 11:53:57 +00:00
TolyaTalamanov
ec92f3fefa Apply comments
* Rename intersectMapWith -> mergeMapWith
* Remove macro
* Add r-value ref
2022-09-16 15:24:13 +00:00
TolyaTalamanov
eb8883160d Support config as part of Infer node in yml 2022-09-15 10:47:13 +00:00
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
Alexander Smorkalov
866191478f
Merge pull request #22037 from xiong-jie-y:py_gapi_add_state_kernel
Add stateful kernel to python G-API
2022-09-09 15:13:22 +03:00
Alexander Smorkalov
c9060b053d
Merge pull request #22451 from dmatveev:dm/abstract_execs
G-API: Introduce abstract base classes for GExecutor and GStreamingExecutor
2022-09-09 13:42:42 +03:00
TolyaTalamanov
7955469f7c Fix problem with handleNewStream functionality 2022-09-06 08:52:35 +01:00
TolyaTalamanov
bf54a370e5 Add tests for stateful kernel functionality 2022-09-04 20:15:53 +01:00
Alexander Alekhin
5bb098ba5d Merge pull request #22456 from TolyaTalamanov:at/onevpl-fixes-linux 2022-09-02 21:55:49 +00:00
Dmitry Matveev
a122f0f248 G-API: Introduce GAbstractStreamingExecutor
Now GStreamingExecutor is its subclass; others to come
2022-08-30 23:50:34 +03:00
Dmitry Matveev
a31fb88fd0 G-API: Introduce GAbstractExecutor
GExecutor is now a subclass of GAbstractExecutor. Other to come
2022-08-30 22:48:29 +03:00
Dmitry Matveev
ed9d4c0b2b G-API: Update ADE to v0.1.2a to fix new Windows warnings 2022-08-26 21:29:56 +03:00
TolyaTalamanov
a1d752bfc0 OneVPL fixes 2022-08-24 17:30:32 +01:00
Anatoliy Talamanov
925ff6241f
Merge pull request #22393 from TolyaTalamanov:at/fix-gapi-vpl-windows-build
* Fix G-API OneVPL compilation

* Fix macro

__WIN32__ -> _WIN32
2022-08-20 20:24:41 +03:00
Dmtiry Matveev
03130548ea G-API: Bump ADE to version 0.1.2 2022-08-18 07:50:22 +03:00
Alexander Smorkalov
885a446b10
Merge pull request #22212 from SergeyIvanov87:gapi_vpl_multiple_devices
G-API: VPL Add VAAPI into tests & VPL sample
2022-08-03 12:34:10 +03:00
HAN Liutong
0ef803950b
Merge pull request #22179 from hanliutong:new-rvv
[GSoC] New universal intrinsic backend for RVV

* Add new rvv backend (partially implemented).

* Modify the framework of Universal Intrinsic.

* Add CV_SIMD macro guards to current UI code.

* Use vlanes() instead of nlanes.

* Modify the UI test.

* Enable the new RVV (scalable) backend.

* Remove whitespace.

* Rename and some others modify.

* Update intrin.hpp but still not work on AVX/SSE

* Update conditional compilation macros.

* Use static variable for vlanes.

* Use max_nlanes for array defining.
2022-07-19 20:02:00 +03:00
SergeyIvanov87
9ffb67478f Address several comments 2022-07-13 18:49:48 +03:00
SergeyIvanov87
1dee848d3e Remove clnn header from sample 2022-07-13 18:07:41 +03:00
SergeyIvanov87
ff31f90b7e Fix sample WIN compilation 2022-07-12 13:08:55 +03:00
SergeyIvanov87
2b2ba534e2 Forbid Rctx in IE for VAAPI temporary, Add preproc VAAPI 2022-07-12 12:41:23 +03:00
SergeyIvanov87
3635b3dee7 Improve UX: autofill cfg param with proper accel type, printout cfg params 2022-07-12 10:54:12 +03:00
SergeyIvanov87
b3b235ebc0 Apply WITHA_VA option in cmake 2022-07-08 17:15:31 +03:00
SergeyIvanov87
f562264674 Add VAAPI into tests & VPL sample 2022-07-08 11:43:56 +03:00
xiong-jie-y
ea2527c2d1 Add python bindings for G-API onnx 2022-06-02 19:09:26 +09:00
Namgoo Lee
24547f40ff remove const from functions returning by value 2022-05-26 21:30:41 +09:00
xiong-jie-y
a3d6994afa Add stateful kernel to python G-API 2022-05-26 01:15:56 +09:00
Alexander Alekhin
bc0d4585b3 Merge pull request #21984 from xiong-jie-y:add_make_capture_for_camera_stream 2022-05-17 21:22:17 +00:00
Alexander Alekhin
9f6f0c7424 Merge pull request #21987 from alalek:gapi_test_reduce_used_memory 2022-05-17 16:26:14 +00:00
xiong-jie-y
c929f1b62f Add make_capture_src for video stream to Python 2022-05-16 20:46:08 +09:00
dbudnikov
3f4ffe7844
Merge pull request #21909 from dbudnikov:dbudnikov/reduce_gapi_tests_number
Reduce G-API tests number

* reduce number of G-API tests

* reduce number of G-API tests

* Address more comments from Dmitry.
2022-05-15 10:07:01 +00:00
Alexander Alekhin
22a00036e2 gapi(test): reduce used amount of memory 2022-05-15 09:41:25 +00:00
Kumataro
602caa9cd6
Merge pull request #21937 from Kumataro:4.x-fix-21911
* Fix warnings for clang15

* Fix warnings: Remove unnecessary code

* Fix warnings: Remove unnecessary code
2022-05-13 17:32:05 +00:00
Sergey
eff5605be5
Merge pull request #21883 from SergeyIvanov87:gapi_vpl_linux
G-API: VPL Source turn on Linux CPU version

* Turn on linux compilation

* Apply comments

* Change new files headline

* Add license header
2022-05-12 08:42:38 +00:00
luzpaz
554d08c3a1
Merge pull request #21775 from luzpaz:typos/gapi
* GAPI: fix various gapi related typos

Fixes source comments and documentation related to gapi code.

* Fix source typos

* Fixed typos requested

* Follow-up typo fix
2022-04-13 17:06:37 +00:00
Alexey Smirnov
7ed557497d
Merge pull request #21504 from smirnov-alexey:as/oak_infer
[GAPI] Support basic inference in OAK backend

* Combined commit which enables basic inference and other extra capabilities of OAK backend

* Remove unnecessary target options from the cmakelist
2022-04-05 21:00:32 +03:00
Anastasiya(Asya) Pronina
91a5e75151
Merge pull request #21731 from AsyaPronina:asyadev/fix_new_stream_event
Fixed handling of new stream, especially for stateful OCV kernels

* Fixed handling of new stream, especially for stateful OCV kernels

* Removed duplication from StateInitOnce tests

* Addressed review comments for PR #21731
- Fixed explanation comments
- Expanded test for stateful OCV kernels in Regular mode

* Addressed review comments for PR #21731
- Moved notification about new stream to the constructor
- Added test on state reset for Regular mode

* Addresed review comments

* Addressed review comments

Co-authored-by: Ruslan Garnov <ruslan.garnov@intel.com>
2022-04-04 17:39:02 +00:00
sivanov-work
84b517f5a0 Fix warning 2022-04-04 08:25:03 +03:00
Sergey Ivanov
f3945fbddb
Merge pull request #21688 from sivanov-work:vpp_ie_integration
G-API: VPP preprocessing GIEBackend integration

* Add ROI in VPP prepro

* Apply comments

* Integration to IE

* Removed extra invocations

* Fix no-vpl compilation

* Fix compilations

* Apply comments

* Use thin wrapper for device & ctx

* Implement Device/Context constructor functions

* Apply samples comment

* Fix compilation

* Fix compilation

* Fix build

* Separate Device&Context from selector, apply other comments

* Fix typo

* Intercept OV exception with pretty print out
2022-04-01 10:06:47 +00:00
Anatoliy Talamanov
9390c56831
Merge pull request #21782 from TolyaTalamanov:at/fix-1d-mat-problems
[G-API] Fix problems with 1D cv::Mat as graph output

* Fix issues with 1D cv::Mat

* Fix cv::Mat::create

* Fix standalone build

* Add test on 1d mat

* Fix warning

* Add additional condition

* Add more tests
2022-03-31 21:00:45 +00:00
Anna Khakimova
be38d4ea93
Merge pull request #21777 from anna-khakimova:ak/convertto_simd
GAPI Fluid: SIMD for ConvertTo.

* GAPI Fluid: SIMD for convertto.

* Applied comments
2022-03-29 21:14:01 +00:00
Anna Khakimova
e5bdab0355
Merge pull request #21728 from anna-khakimova:ak/resize_f32c1_avx_simd
GAPI Fluid: SIMD AVX2 Resize F32C1.

* GAPI Fluid: Resize F32C1 scalar.

* Final version

* GAPI Fluid: SIMD AVX2 for Resize F32C1.

* Applied comments.

* Deleted warning suppression.

* Applied comments.
2022-03-25 18:11:01 +03:00
Anatoliy Talamanov
9dd8e4df7f
Merge pull request #21719 from TolyaTalamanov:at/pipeline_modeling_tool-skip-frames-for-nodes
[G-API] Pipeline modeling tool: Skip frames

* Add skip feature

* Refactoring

* Fix warning

* Put more comments

* Fix comments to review

* Agregate common params into structure

* Fix warning

* Clean up & add test

* Add assert

* Fix warning on Mac

* Update modules/gapi/samples/pipeline_modeling_tool.cpp

Co-authored-by: Dmitry Matveev <dmitry.matveev@intel.com>
2022-03-25 08:22:45 +00:00
Anatoliy Talamanov
d98e07c3d3
Merge pull request #21660 from TolyaTalamanov:at/handle-exception-in-streamingexecutor
[G-API] Handle exceptions in streaming executor

* Handle exceptions in streaming executor

* Rethrow exception in non-streaming executor

* Clean up

* Put more tests

* Handle exceptions in IE backend

* Handle exception in IE callbacks

* Handle exception in GExecutor

* Handle all exceptions in IE backend

* Not only (std::exception& e)

* Fix comments to review

* Handle input exception in generic way

* Fix comment

* Clean up

* Apply review comments

* Put more comments
* Fix alignment
* Move test outside of HAVE_NGRAPH

* Fix compilation
2022-03-25 08:19:53 +00:00
Alexander Alekhin
63c865ace6 Merge pull request #21746 from anna-khakimova:ak/dynamic_dispatch_sub 2022-03-21 17:10:40 +00:00