Skip to content

Commit aee859d

Browse files
jane-inteljane-intel
committed
Merge remote-tracking branch 'upstream/master' into attribute_pattern_matching
Signed-off-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com>
2 parents 19091b3 + 1cf8eda commit aee859d

File tree

43 files changed

+214
-75
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

43 files changed

+214
-75
lines changed

‎.github/actions/common/artifact_utils.py

+3-3
Original file line numberDiff line numberDiff line change
@@ -18,10 +18,10 @@ def add_common_args(parser: argparse.ArgumentParser):
1818
default=os.getenv('ARTIFACTS_SHARE'))
1919
group = parser.add_mutually_exclusive_group(required=True)
2020
group.add_argument('-d', '--storage_dir', help='Subdirectory name for artifacts, same as product type',
21-
choices=[platform_key.value for platform_key in ProductType])
22-
group.add_argument('-p', '--platform', type=str,
21+
choices=[product_type.value for product_type in ProductType], type=str.lower)
22+
group.add_argument('-p', '--platform', type=str.lower,
2323
help='Platform for which to restore artifacts. Used if storage_dir is not set',
24-
choices=[product_type.value for product_type in PlatformKey])
24+
choices=[platform_key.value for platform_key in PlatformKey])
2525

2626

2727
def get_event_type(event_name: str = os.getenv('GITHUB_EVENT_NAME')) -> str:

‎.github/actions/common/constants.py

+4-4
Original file line numberDiff line numberDiff line change
@@ -14,10 +14,10 @@ class EventType(Enum):
1414
'public_linux_ubuntu_22_04_x86_64_release',
1515
'public_linux_ubuntu_22_04_dpcpp_x86_64_release',
1616
'public_linux_ubuntu_24_04_x86_64_release',
17-
'public_windows_vs2019_Release',
18-
'public_windows_vs2019_Debug',
19-
'public_windows_vs2022_Release',
20-
'public_windows_vs2022_Debug',
17+
'public_windows_vs2019_release',
18+
'public_windows_vs2019_debug',
19+
'public_windows_vs2022_release',
20+
'public_windows_vs2022_debug',
2121
'public_manylinux2014_x86_64_release',
2222
)
2323
ProductType = Enum('ProductType', {t.upper(): t for t in productTypes})

‎README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@ Check out the [OpenVINO Cheat Sheet](https://docs.openvino.ai/2025/_static/downl
3535
pip install -U openvino
3636
```
3737

38-
Check [system requirements](https://docs.openvino.ai/2025/about-openvino/system-requirements.html) and [supported devices](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) for detailed information.
38+
Check [system requirements](https://docs.openvino.ai/2025/about-openvino/system-requirements.html) and [supported devices](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) for detailed information.
3939

4040
## Tutorials and Examples
4141

‎docs/articles_en/get-started/learn-openvino/openvino-samples/benchmark-tool.rst

+2-2
Original file line numberDiff line numberDiff line change
@@ -382,7 +382,7 @@ available options and parameters:
382382
-t TIME, --time TIME Optional. Time in seconds to execute topology.
383383
384384
-api {sync,async}, --api_type {sync,async}
385-
Optional. Enable using sync/async API. Default value is async.
385+
Optional. Enable using sync/async API. When hint is throughput, default value is async. When hint is latency, default value is sync.
386386
387387
388388
Input shapes:
@@ -557,7 +557,7 @@ available options and parameters:
557557
-c <absolute_path> Required for GPU custom kernels. Absolute path to an .xml file with the kernels description.
558558
-cache_dir <path> Optional. Enables caching of loaded models to specified directory. List of devices which support caching is shown at the end of this message.
559559
-load_from_file Optional. Loads model from file directly without read_model. All CNNNetwork options (like re-shape) will be ignored
560-
-api <sync/async> Optional. Enable Sync/Async API. Default value is "async".
560+
-api <sync/async> Optional. Enable Sync/Async API. When hint is throughput, default value is "async". When hint is latency, default value is "sync".
561561
-nireq <integer> Optional. Number of infer requests. Default value is determined automatically for device.
562562
-nstreams <integer> Optional. Number of streams to use for inference on the CPU or GPU devices (for HETERO and MULTI device cases use format <dev1>:<nstreams1>, <dev2>:<nstreams2> or just <nstreams>). Default value is determined automatically for a device.Please note that although the automatic selection usually provides a reasonable performance, it still may be non - optimal for some cases, especially for very small models. See sample's README for more details. Also, using nstreams>1 is inherently throughput-oriented option, while for the best-latency estimations the number of streams should be set to 1.
563563
-inference_only Optional. Measure only inference stage. Default option for static models. Dynamic models are measured in full mode which includes inputs setup stage, inference only mode available for them with single input data shape only. To enable full mode for static models pass "false" value to this argument: ex. "-inference_only=false".

‎samples/c/hello_nv12_input_classification/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@ For more detailed information on how this sample works, check the dedicated [art
1010

1111
| Options | Values |
1212
| ----------------------------| ---------------------------------------------------------------------------------------------------------------------|
13-
| Model Format | OpenVINO Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
13+
| Model Format | OpenVINO Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
1414
| Validated images | An uncompressed image in the NV12 color format - \*.yuv |
15-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
15+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1616
| Other language realization | [C++](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/hello-nv12-input-classification.html) |
1717

1818
The following C++ API is used in the application:

‎samples/cpp/benchmark/sync_benchmark/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ For more detailed information on how this sample works, check the dedicated [art
1212
| | [face-detection-0200](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/face-detection-0200) |
1313
| Model Format | OpenVINO™ toolkit Intermediate Representation |
1414
| | (\*.xml + \*.bin), ONNX (\*.onnx) |
15-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
15+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1616
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/sync-benchmark.html) |
1717

1818
The following C++ API is used in the application:

‎samples/cpp/benchmark/throughput_benchmark/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ For more detailed information on how this sample works, check the dedicated [art
1414
| | [face-detection-](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/face-detection-0200) |
1515
| Model Format | OpenVINO™ toolkit Intermediate Representation |
1616
| | (\*.xml + \*.bin), ONNX (\*.onnx) |
17-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
17+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1818
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/throughput-benchmark.html) |
1919

2020
The following C++ API is used in the application:

‎samples/cpp/benchmark_app/benchmark_app.hpp

+4-2
Original file line numberDiff line numberDiff line change
@@ -98,7 +98,9 @@ static const char layout_message[] =
9898
"For example, \"input1[NCHW],input2[NC]\" or \"[NCHW]\" in case of one input size.";
9999

100100
/// @brief message for execution mode
101-
static const char api_message[] = "Optional. Enable Sync/Async API. Default value is \"async\".";
101+
static const char api_message[] =
102+
"Optional. Enable Sync/Async API. When hint is throughput, default value is \"async\". "
103+
"When hint is latency, default value is \"sync\".";
102104

103105
/// @brief message for #streams for CPU inference
104106
static const char infer_num_streams_message[] =
@@ -303,7 +305,7 @@ DEFINE_string(cache_dir, "", cache_dir_message);
303305
DEFINE_bool(load_from_file, false, load_from_file_message);
304306

305307
/// @brief Define execution mode
306-
DEFINE_string(api, "async", api_message);
308+
DEFINE_string(api, "", api_message);
307309

308310
/// @brief Number of infer requests in parallel
309311
DEFINE_uint64(nireq, 0, infer_requests_count_message);

‎samples/cpp/benchmark_app/main.cpp

+3
Original file line numberDiff line numberDiff line change
@@ -58,6 +58,9 @@ bool parse_and_check_command_line(int argc, char* argv[]) {
5858
show_usage();
5959
throw std::logic_error("The percentile value is incorrect. The applicable values range is [1, 100].");
6060
}
61+
if (FLAGS_api == "") {
62+
FLAGS_api = FLAGS_hint == "latency" ? "sync" : "async";
63+
}
6164
if (FLAGS_api != "async" && FLAGS_api != "sync") {
6265
throw std::logic_error("Incorrect API. Please set -api option to `sync` or `async` value.");
6366
}

‎samples/cpp/classification_sample_async/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ For more detailed information on how this sample works, check the dedicated [art
1313
| Options | Values |
1414
| ---------------------------| -------------------------------------------------------------------------------------------------------------------------------------|
1515
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
16-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
16+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1717
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/image-classification-async.html) |
1818

1919
The following C++ API is used in the application:

‎samples/cpp/hello_classification/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ For more detailed information on how this sample works, check the dedicated [art
1111
| Options | Values |
1212
| ----------------------------| ------------------------------------------------------------------------------------------------------------------------------|
1313
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
14-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
14+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1515
| Other language realization | [Python, C](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/hello-classification.html), |
1616

1717
The following C++ API is used in the application:

‎samples/cpp/hello_nv12_input_classification/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ For more detailed information on how this sample works, check the dedicated [art
1010
| ----------------------------| --------------------------------------------------------------------------------------------------------------------------------|
1111
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
1212
| Validated images | An uncompressed image in the NV12 color format - \*.yuv |
13-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
13+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1414
| Other language realization | [C](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/hello-nv12-input-classification.html) |
1515

1616

‎samples/cpp/hello_query_device/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ For more detailed information on how this sample works, check the dedicated [art
88

99
| Options | Values |
1010
| ------------------------------| ----------------------------------------------------------------------------------------------------------------------------|
11-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
11+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1212
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/hello-query-device.html) |
1313

1414
The following C++ API is used in the application:

‎samples/cpp/hello_reshape_ssd/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ For more detailed information on how this sample works, check the dedicated [art
1111
| ----------------------------| -----------------------------------------------------------------------------------------------------------------------------------------|
1212
| Validated Models | [person-detection-retail-0013](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/person-detection-retail-0013) |
1313
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
14-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
14+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1515
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/hello-reshape-ssd.html) |
1616

1717
The following C++ API is used in the application:

‎samples/cpp/model_creation_sample/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ For more detailed information on how this sample works, check the dedicated [art
1313
| Validated Models | LeNet |
1414
| Model Format | model weights file (\*.bin) |
1515
| Validated images | single-channel ``MNIST ubyte`` images |
16-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
16+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1717
| Other language realization | [Python](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/model-creation.html) |
1818

1919
The following C++ API is used in the application:

‎samples/python/benchmark/sync_benchmark/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ For more detailed information on how this sample works, check the dedicated [art
1212
| | [face-detection-0200](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/face-detection-0200) |
1313
| Model Format | OpenVINO™ toolkit Intermediate Representation |
1414
| | (\*.xml + \*.bin), ONNX (\*.onnx) |
15-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
15+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1616
| Other language realization | [C++](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/sync-benchmark.html) |
1717

1818
The following Python API is used in the application:

‎samples/python/benchmark/throughput_benchmark/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ For more detailed information on how this sample works, check the dedicated [art
1414
| | [face-detection-0200](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/face-detection-0200) |
1515
| Model Format | OpenVINO™ toolkit Intermediate Representation |
1616
| | (\*.xml + \*.bin), ONNX (\*.onnx) |
17-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
17+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1818
| Other language realization | [C++](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/sync-benchmark.html) |
1919

2020
The following Python API is used in the application:

‎samples/python/classification_sample_async/README.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ For more detailed information on how this sample works, check the dedicated [art
1111
| Options | Values |
1212
| ---------------------------| -----------------------------------------------------------------------------------------------------------------|
1313
| Model Format | OpenVINO™ toolkit Intermediate Representation (.xml + .bin), ONNX (.onnx) |
14-
| Supported devices | [All](https://docs.openvino.ai/2025/about-openvino/compatibility-and-support/supported-devices.html) |
14+
| Supported devices | [All](https://docs.openvino.ai/2025/documentation/compatibility-and-support/supported-devices.html) |
1515
| Other language realization | [C++](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/image-classification-async.html) |
1616

1717
The following Python API is used in the application:

0 commit comments

Comments
 (0)