[C API DOC] Reconstruct the guide about integration with OpenVINO Runtime for C
Signed-off-by: xuejun <Xuejun.Zhai@intel.com>
This commit is contained in:
xuejun
parent
eb0493ea43
commit
9552054e7e
@ -18,7 +18,38 @@ Following these steps, you can implement a typical OpenVINO™ Runtime inference
|
||||
|
||||
![ie_api_use_cpp]
|
||||
|
||||
## Step 1. Create OpenVINO™ Runtime Core
|
||||
## Step 1. Create Cmake Script
|
||||
|
||||
This step may differ for different projects. In this example, a C++ & C application is used, together with CMake for project configuration.
|
||||
`
|
||||
Create a structure for the project:
|
||||
project/
|
||||
├── CMakeLists.txt - CMake file to build
|
||||
├── ... - Additional folders like includes/
|
||||
└── src/ - source folder
|
||||
└── main.c - [Optional] For C sample
|
||||
└── main.cpp - [Optional] For C++ sample
|
||||
build/ - build directory
|
||||
...
|
||||
`
|
||||
|
||||
@sphinxtabset
|
||||
|
||||
@sphinxtab{C++}
|
||||
|
||||
@snippet snippets/CMakeLists.txt cmake:integration_example_cpp
|
||||
|
||||
@endsphinxtab
|
||||
|
||||
@sphinxtab{C}
|
||||
|
||||
@snippet snippets/CMakeLists.txt cmake:integration_example_c
|
||||
|
||||
@endsphinxtab
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 2. Create OpenVINO™ Runtime Core
|
||||
|
||||
Include next files to work with OpenVINO™ Runtime:
|
||||
|
||||
@ -68,7 +99,7 @@ Use the following code to create OpenVINO™ Core to manage available devices an
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 2. Compile the Model
|
||||
## Step 3. Compile the Model
|
||||
|
||||
`ov::CompiledModel` class represents a device specific compiled model. `ov::CompiledModel` allows you to get information inputs or output ports by a tensor name or index. This approach is aligned with the majority of frameworks.
|
||||
|
||||
@ -181,7 +212,7 @@ The code above creates a compiled model associated with a single hardware device
|
||||
It is possible to create as many compiled models as needed and use them simultaneously (up to the limitation of the hardware resources).
|
||||
To learn how to change the device configuration, read the [Query device properties](./supported_plugins/config_properties.md) article.
|
||||
|
||||
## Step 3. Create an Inference Request
|
||||
## Step 4. Create an Inference Request
|
||||
|
||||
`ov::InferRequest` class provides methods for model inference in OpenVINO™ Runtime. Create an infer request using the following code (see [InferRequest detailed documentation](./ov_infer_request.md) for more details):
|
||||
|
||||
@ -207,7 +238,7 @@ To learn how to change the device configuration, read the [Query device properti
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 4. Set Inputs
|
||||
## Step 5. Set Inputs
|
||||
|
||||
You can use external memory to create `ov::Tensor` and use the `ov::InferRequest::set_input_tensor` method to put this tensor on the device:
|
||||
|
||||
@ -233,7 +264,7 @@ You can use external memory to create `ov::Tensor` and use the `ov::InferRequest
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 5. Start Inference
|
||||
## Step 6. Start Inference
|
||||
|
||||
OpenVINO™ Runtime supports inference in either synchronous or asynchronous mode. Using the Async API can improve application's overall frame-rate: instead of waiting for inference to complete, the app can keep working on the host while the accelerator is busy. You can use `ov::InferRequest::start_async` to start model inference in the asynchronous mode and call `ov::InferRequest::wait` to wait for the inference results:
|
||||
|
||||
@ -261,7 +292,7 @@ OpenVINO™ Runtime supports inference in either synchronous or asynchronous mod
|
||||
|
||||
This section demonstrates a simple pipeline. To get more information about other ways to perform inference, read the dedicated ["Run inference" section](./ov_infer_request.md).
|
||||
|
||||
## Step 6. Process the Inference Results
|
||||
## Step 7. Process the Inference Results
|
||||
|
||||
Go over the output tensors and process the inference results.
|
||||
|
||||
@ -287,7 +318,7 @@ Go over the output tensors and process the inference results.
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 7. Release the allocated objects (only for C)
|
||||
## Step 8. Release the allocated objects (only for C)
|
||||
|
||||
To avoid memory leak, applications developed with C API need to release the allocated objects in order.
|
||||
|
||||
@ -301,33 +332,6 @@ To avoid memory leak, applications developed with C API need to release the allo
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
## Step 8. Link and Build Your Application with OpenVINO™ Runtime (example)
|
||||
|
||||
This step may differ for different projects. In this example, a C++ & C application is used, together with CMake for project configuration.
|
||||
|
||||
For details on additional CMake build options, refer to the [CMake page](https://cmake.org/cmake/help/latest/manual/cmake.1.html#manual:cmake(1)).
|
||||
|
||||
@sphinxtabset
|
||||
|
||||
@sphinxtab{C++}
|
||||
|
||||
@snippet docs/snippets/src/main.cpp part7
|
||||
|
||||
@snippet snippets/CMakeLists.txt cmake:integration_example_cpp
|
||||
|
||||
@endsphinxtab
|
||||
|
||||
@sphinxtab{C}
|
||||
|
||||
@snippet docs/snippets/src/main.c part7
|
||||
|
||||
@snippet snippets/CMakeLists.txt cmake:integration_example_c
|
||||
|
||||
@endsphinxtab
|
||||
|
||||
@endsphinxtabset
|
||||
|
||||
|
||||
To build your project using CMake with the default build tools currently available on your machine, execute the following commands:
|
||||
|
||||
```sh
|
||||
|
||||
@ -35,7 +35,7 @@ ov_core_compile_model_from_file(core, "model.pdmodel", device_name, 0, &compiled
|
||||
|
||||
//! [part2_4]
|
||||
// Construct a model
|
||||
ov_model_t* model = NULL; // need to free by ov_model_free(model)
|
||||
ov_model_t* model = NULL;
|
||||
ov_core_read_model(core, "model.xml", NULL, &model);
|
||||
ov_compiled_model_t* compiled_model = NULL;
|
||||
ov_core_compile_model(core, model, device_name, 0, &compiled_model);
|
||||
@ -47,8 +47,12 @@ ov_infer_request_t* infer_request = NULL;
|
||||
ov_compiled_model_create_infer_request(compiled_model, &infer_request);
|
||||
//! [part3]
|
||||
|
||||
ov_shape_t input_shape = {0, NULL};
|
||||
ov_output_port_t* input_port = NULL;
|
||||
ov_model_input(model, &input_port);
|
||||
ov_shape_t input_shape;
|
||||
ov_port_get_shape(input_port, &input_shape);
|
||||
void* img_data = NULL;
|
||||
// read img ...
|
||||
ov_element_type_e input_type = U8;
|
||||
//! [part4]
|
||||
ov_tensor_t* tensor = NULL;
|
||||
@ -69,6 +73,7 @@ ov_infer_request_get_output_tensor_by_index(infer_request, 0, &output_tensor);
|
||||
//! [part6]
|
||||
|
||||
//! [part8]
|
||||
ov_output_port_free(input_port);
|
||||
ov_tensor_free(output_tensor);
|
||||
ov_tensor_free(tensor);
|
||||
ov_infer_request_free(infer_request);
|
||||
@ -79,16 +84,3 @@ ov_core_free(core);
|
||||
|
||||
return 0;
|
||||
}
|
||||
/*
|
||||
//! [part7]
|
||||
// Create a structure for the project:
|
||||
project/
|
||||
├── CMakeLists.txt - CMake file to build
|
||||
├── ... - Additional folders like includes/
|
||||
└── src/ - source folder
|
||||
└── main.c
|
||||
build/ - build directory
|
||||
...
|
||||
|
||||
//! [part7]
|
||||
*/
|
||||
@ -67,16 +67,4 @@ const float *output_buffer = output.data<const float>();
|
||||
//! [part6]
|
||||
return 0;
|
||||
}
|
||||
/*
|
||||
//! [part7]
|
||||
// Create a structure for the project:
|
||||
project/
|
||||
├── CMakeLists.txt - CMake file to build
|
||||
├── ... - Additional folders like includes/
|
||||
└── src/ - source folder
|
||||
└── main.cpp
|
||||
build/ - build directory
|
||||
...
|
||||
|
||||
//! [part7]
|
||||
*/
|
||||
|
||||
Loading…
Reference in New Issue
Block a user