未验证 提交 9d6480c7 编写于 作者: O openharmony_ci 提交者: Gitee

!22976 翻译已完成21897+22586

Merge pull request !22976 from shawn_he/22586-d
......@@ -19,13 +19,14 @@ The environment requirements for the Neural Network Runtime are as follows:
- Development environment: Ubuntu 18.04 or later.
- Access device: a standard device running OpenHarmony. The built-in hardware accelerator driver has been connected to the Neural Network Runtime through an HDI API.
The Neural Network Runtime is opened to external systems through OpenHarmony Native APIs. Therefore, you need to use the Native development suite of the OpenHarmony to compile Neural Network Runtime applications.
The Neural Network Runtime is opened to external systems through OpenHarmony Native APIs. Therefore, you need to use the Native development suite of OpenHarmony to compile Neural Network Runtime applications.
### Environment Setup
1. Start the Ubuntu server.
2. Copy the package of the Native development suite to the root directory of the current user.
3. Decompress the package of the Native development suite.
```shell
unzip native-linux-{version number}.zip
```
......@@ -470,16 +471,25 @@ The development process of the Neural Network Runtime consists of three phases:
> The IR graphs of the model need to be passed to the hardware driver layer, so that the HDI service compiles the IR graphs into a computing graph dedicated to hardware. The compilation process is time-consuming. The Neural Network Runtime supports the computing graph cache feature. It can cache the computing graphs compiled by the HDI service to the device storage. If the same model is compiled on the same acceleration chip next time, you can specify the cache path so that the Neural Network Runtime can directly load the computing graphs in the cache file, reducing the compilation time.
Check the cached files in the cache directory.
```shell
ls /data/local/tmp
```
The command output is as follows:
```text
# 0.nncache cache_info.nncache
```
If the cache is no longer used, manually delete the cache files.
```shell
rm /data/local/tmp/*nncache
```
\ No newline at end of file
```
## Samples
The following sample is provided to help you understand how to connect a third-party AI inference framework to the Neural Network Runtime:
- [Development Guide for Connecting TensorFlow Lite to NNRt Delegate](https://gitee.com/openharmony/ai_neural_network_runtime/tree/master/example/deep_learning_framework)
......@@ -28,7 +28,7 @@ Adds a contact. This API uses an asynchronous callback to return the result.
| Name | Type | Mandatory| Description |
| -------- | --------------------------- | ---- | ------------------------------ |
| contact | [Contact](#contact) | Yes | Contact information. |
| callback | AsyncCallback<number> | Yes | Callback used to return the contact ID.|
| callback | AsyncCallback<number> | Yes | Callback used to return the result, which is a contact ID.|
**Example**
......@@ -273,7 +273,7 @@ Checks whether the ID of this contact is in the local address book. This API use
| Name | Type | Mandatory| Description |
| -------- | ---------------------------- | ---- | ------------------------------------------------------------ |
| id | number | Yes | Contact ID. Each contact corresponds to one ID. |
| callback | AsyncCallback<boolean> | Yes | Callback used to return a boolean value. The value **true** indicates that the contact ID is in the local address book, and the value **false** indicates the opposite.|
| callback | AsyncCallback<boolean> | Yes | Callback used to return the result. The value **true** indicates that the contact ID is in the local address book, and the value **false** indicates the opposite.|
**Example**
......@@ -1694,11 +1694,11 @@ Defines an application that creates the contact.
**System capability**: SystemCapability.Applications.ContactsData
| Name | Type | Readable| Writable| Description |
| ----------- | -------- | ---- | ---- | ---------- |
| bundleName | string | Yes | No | Bundle name of an application. |
| displayName | string | Yes | No | Application name.|
| holderId | number | Yes | Yes | Application ID. |
| Name | Type | Readable| Writable| Description |
| ----------- | ------ | ---- | ---- | ------------ |
| bundleName | string | Yes | No | Bundle name.|
| displayName | string | Yes | No | Application name. |
| holderId | number | Yes | Yes | Application ID. |
**Example**
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册