@@ -103,7 +103,7 @@ A: After MindSpore is installed on a CPU hardware platform, run the `python -c'i
Q: What can I do if the LSTM example on the official website cannot run on Ascend?
A: Currently, the LSTM runs only on a GPU or CPU and does not support the hardware environment. You can click [here](https://www.mindspore.cn/docs/en/master/operator_list.html) to view the supported operators.
A: Currently, the LSTM runs only on a GPU or CPU and does not support the hardware environment. You can click [here](https://www.mindspore.cn/docs/en/r0.7/operator_list.html) to view the supported operators.
<br/>
...
...
@@ -121,7 +121,7 @@ A: MindSpore uses protocol buffers (protobuf) to store training parameters and c
Q: How do I use models trained by MindSpore on Ascend 310?
A: Ascend 310 supports the offline model (OM). Therefore, you need to export the Open Neural Network Exchange (ONNX) or Ascend intermediate representation (AIR) model and then convert it into OM supported by Ascend 310. For details, see [Multi-Platform Inference](https://www.mindspore.cn/tutorial/en/master/use/multi_platform_inference.html).
A: Ascend 310 supports the offline model (OM). Therefore, you need to export the Open Neural Network Exchange (ONNX) or Ascend intermediate representation (AIR) model and then convert it into OM supported by Ascend 310. For details, see [Multi-Platform Inference](https://www.mindspore.cn/tutorial/en/r0.7/use/multi_platform_inference.html).
<br/>
...
...
@@ -133,19 +133,19 @@ A: When building a network, use `if self.training: x = dropput(x)`. During verif
Q: Where can I view the sample code or tutorial of MindSpore training and inference?
A: Please visit the [MindSpore official website](https://www.mindspore.cn/tutorial/en/master/index.html).
A: Please visit the [MindSpore official website](https://www.mindspore.cn/tutorial/en/r0.7/index.html).
<br/>
Q: What types of model is currently supported by MindSpore for training?
A: MindSpore has basic support for common training scenarios, please refer to [Release note](https://gitee.com/mindspore/mindspore/blob/master/RELEASE.md) for detailed information.
A: MindSpore has basic support for common training scenarios, please refer to [Release note](https://gitee.com/mindspore/mindspore/blob/r0.7/RELEASE.md) for detailed information.
<br/>
Q: What are the available recommendation or text generation networks or models provided by MindSpore?
A: Currently, recommendation models such as Wide & Deep, DeepFM, and NCF are under development. In the natural language processing (NLP) field, Bert\_NEZHA is available and models such as MASS are under development. You can rebuild the network into a text generation network based on the scenario requirements. Please stay tuned for updates on the [MindSpore Model Zoo](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).
A: Currently, recommendation models such as Wide & Deep, DeepFM, and NCF are under development. In the natural language processing (NLP) field, Bert\_NEZHA is available and models such as MASS are under development. You can rebuild the network into a text generation network based on the scenario requirements. Please stay tuned for updates on the [MindSpore Model Zoo](https://gitee.com/mindspore/mindspore/tree/r0.7/model_zoo).
<br/>
...
...
@@ -163,7 +163,7 @@ A: Ascend 310 can only be used for inference. MindSpore supports training on Asc
Q: Does MindSpore require computing units such as GPUs and NPUs? What hardware support is required?
A: MindSpore currently supports CPU, GPU, Ascend, and NPU. Currently, you can try out MindSpore through Docker images on laptops or in environments with GPUs. Some models in MindSpore Model Zoo support GPU-based training and inference, and other models are being improved. For distributed parallel training, MindSpore supports multi-GPU training. You can obtain the latest information from [Road Map](https://www.mindspore.cn/docs/en/master/roadmap.html) and [project release notes](https://gitee.com/mindspore/mindspore/blob/master/RELEASE.md).
A: MindSpore currently supports CPU, GPU, Ascend, and NPU. Currently, you can try out MindSpore through Docker images on laptops or in environments with GPUs. Some models in MindSpore Model Zoo support GPU-based training and inference, and other models are being improved. For distributed parallel training, MindSpore supports multi-GPU training. You can obtain the latest information from [Road Map](https://www.mindspore.cn/docs/en/r0.7/roadmap.html) and [project release notes](https://gitee.com/mindspore/mindspore/blob/r0.7/RELEASE.md).
<br/>
...
...
@@ -175,13 +175,13 @@ A: MindSpore provides pluggable device management interface so that developer co
Q: What is the relationship between MindSpore and ModelArts? Can MindSpore be used on ModelArts?
A: ModelArts is an online training and inference platform on HUAWEI CLOUD. MindSpore is a Huawei deep learning framework. You can view the tutorials on the [MindSpore official website](https://www.mindspore.cn/tutorial/zh-CN/master/advanced_use/use_on_the_cloud.html) to learn how to train MindSpore models on ModelArts.
A: ModelArts is an online training and inference platform on HUAWEI CLOUD. MindSpore is a Huawei deep learning framework. You can view the tutorials on the [MindSpore official website](https://www.mindspore.cn/tutorial/zh-CN/r0.7/advanced_use/use_on_the_cloud.html) to learn how to train MindSpore models on ModelArts.
<br/>
Q: Does MindSpore support Windows 10?
A: The MindSpore CPU version can be installed on Windows 10. For details about the installation procedure, please refer to the [MindSpore official website tutorial](https://www.mindspore.cn/tutorial/zh-CN/master/advanced_use/mindspore_cpu_win_install.html)
A: The MindSpore CPU version can be installed on Windows 10. For details about the installation procedure, please refer to the [MindSpore official website tutorial](https://www.mindspore.cn/tutorial/zh-CN/r0.7/advanced_use/mindspore_cpu_win_install.html)
## Backend Running
...
...
@@ -207,7 +207,7 @@ A: The problem is that the Graph mode is selected but the PyNative mode is used.
- PyNative mode: dynamic graph mode. In this mode, operators in the neural network are delivered and executed one by one, facilitating the compilation and debugging of the neural network model.
- Graph mode: static graph mode. In this mode, the neural network model is compiled into an entire graph and then delivered for execution. This mode uses technologies such as graph optimization to improve the running performance and facilitates large-scale deployment and cross-platform running.
You can select a proper mode and writing method to complete the training by referring to the official website [tutorial](https://www.mindspore.cn/tutorial/en/master/advanced_use/debugging_in_pynative_mode.html).
You can select a proper mode and writing method to complete the training by referring to the official website [tutorial](https://www.mindspore.cn/tutorial/en/r0.7/advanced_use/debugging_in_pynative_mode.html).
## Programming Language Extensions
...
...
@@ -253,7 +253,7 @@ A: The TensorFlow's object detection pipeline API belongs to the TensorFlow's Mo
Q: How do I migrate scripts or models of other frameworks to MindSpore?
A: For details about script or model migration, please visit the [MindSpore official website](https://www.mindspore.cn/tutorial/en/master/advanced_use/network_migration.html).
A: For details about script or model migration, please visit the [MindSpore official website](https://www.mindspore.cn/tutorial/en/r0.7/advanced_use/network_migration.html).
1. The preceding performance is obtained based on ModelArts, the HUAWEI CLOUD AI development platform. It is the average performance obtained by the Ascend 910 AI processor during the overall training process.
2. For details about other open source frameworks, see [ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/ConvNets/resnet50v1.5).
2. For details about other open source frameworks, see [ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/r0.7/TensorFlow/Classification/ConvNets/resnet50v1.5).
### BERT
...
...
@@ -39,7 +39,7 @@ For details about the MindSpore networks, see [Model Zoo](https://gitee.com/mind
1. The preceding performance is obtained based on ModelArts, the HUAWEI CLOUD AI development platform. The network contains 24 hidden layers, the sequence length is 128 tokens, and the vocabulary contains 21128 tokens.
2. For details about other open source frameworks, see [BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT).
2. For details about other open source frameworks, see [BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/r0.7/TensorFlow/LanguageModeling/BERT).
### Wide & Deep (data parallel)
...
...
@@ -49,7 +49,7 @@ For details about the MindSpore networks, see [Model Zoo](https://gitee.com/mind
1. The preceding performance is obtained based on Atlas 800, and the model is data parallel.
2. For details about other open source frameworks, see [Wide & Deep For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Recommendation/WideAndDeep)。
2. For details about other open source frameworks, see [Wide & Deep For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/r0.7/TensorFlow/Recommendation/WideAndDeep)。
### Wide & Deep (Host-Device model parallel)
...
...
@@ -61,4 +61,4 @@ For details about the MindSpore networks, see [Model Zoo](https://gitee.com/mind
1. The preceding performance is obtained based on Atlas 800, and the model is model parallel.
2. For details about other open source frameworks, see [Wide & Deep For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Recommendation/WideAndDeep)。
2. For details about other open source frameworks, see [Wide & Deep For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/r0.7/TensorFlow/Recommendation/WideAndDeep)。
MindSpore can compile user source code based on the Python syntax into computational graphs, and can convert common functions or instances inherited from nn.Cell into computational graphs. Currently, MindSpore does not support conversion of any Python source code into computational graphs. Therefore, there are constraints on source code compilation, including syntax constraints and network definition constraints. As MindSpore evolves, the constraints may change.
...
...
@@ -206,8 +206,8 @@ Currently, the following syntax is not supported in network constructors:
## Network Definition Constraints
### Instance Types on the Entire Network
* Common Python function with the [@ms_function](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.html#mindspore.ms_function) decorator.
* Cell subclass inherited from [nn.Cell](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.nn.html#mindspore.nn.Cell).
* Common Python function with the [@ms_function](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.html#mindspore.ms_function) decorator.
* Cell subclass inherited from [nn.Cell](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.nn.html#mindspore.nn.Cell).
### Network Input Type
* The training data input parameters of the entire network must be of the Tensor type.
...
...
@@ -220,13 +220,13 @@ Currently, the following syntax is not supported in network constructors:
| Category | Content
| :----------- |:--------
| `Cell` instance |[mindspore/nn/*](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.nn.html), and custom [Cell](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.nn.html#mindspore.nn.Cell).
| `Cell` instance |[mindspore/nn/*](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.nn.html), and custom [Cell](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.nn.html#mindspore.nn.Cell).
| Member function of a `Cell` instance | Member functions of other classes in the construct function of Cell can be called.
| Function | Custom Python functions and system functions listed in the preceding content.
| Dataclass instance | Class decorated with @dataclass.
| Operator generated by constexpr |Uses the value generated by [@constexpr](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.ops.html#mindspore.ops.constexpr) to calculate operators.
| Operator generated by constexpr |Uses the value generated by [@constexpr](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.ops.html#mindspore.ops.constexpr) to calculate operators.
@@ -71,4 +71,4 @@ RESTful API is used for data interaction between the MindInsight frontend and ba
#### File API Design
Data interaction between MindSpore and MindInsight uses the data format defined by [Protocol Buffer](https://developers.google.cn/protocol-buffers/docs/pythontutorial).
The main entry is the [summary.proto file](https://gitee.com/mindspore/mindinsight/blob/master/mindinsight/datavisual/proto_files/mindinsight_summary.proto). A message object of a computational graph is defined as `GraphProto`. For details about `GraphProto`, see the [anf_ir.proto file](https://gitee.com/mindspore/mindinsight/blob/master/mindinsight/datavisual/proto_files/mindinsight_anf_ir.proto).
\ No newline at end of file
The main entry is the [summary.proto file](https://gitee.com/mindspore/mindinsight/blob/r0.7/mindinsight/datavisual/proto_files/mindinsight_summary.proto). A message object of a computational graph is defined as `GraphProto`. For details about `GraphProto`, see the [anf_ir.proto file](https://gitee.com/mindspore/mindinsight/blob/r0.7/mindinsight/datavisual/proto_files/mindinsight_anf_ir.proto).
@@ -55,7 +55,7 @@ Figure 2 shows tensors recorded by a user in a form of a histogram.
### API Design
In tensor visualization, there are file API and RESTful API. The file API is the [summary.proto](https://gitee.com/mindspore/mindspore/blob/master/mindspore/ccsrc/utils/summary.proto) file, which is used for data interconnection between MindInsight and MindSpore. RESTful API is an internal API used for data interaction between the MindInsight frontend and backend.
In tensor visualization, there are file API and RESTful API. The file API is the [summary.proto](https://gitee.com/mindspore/mindspore/blob/r0.7/mindspore/ccsrc/utils/summary.proto) file, which is used for data interconnection between MindInsight and MindSpore. RESTful API is an internal API used for data interaction between the MindInsight frontend and backend.
#### File API Design
...
...
@@ -100,4 +100,4 @@ The `summary.proto` file is the main entry. TensorProto data is stored in the su
repeated Value value = 1;
}
```
TensorProto is defined in the [anf_ir.proto](https://gitee.com/mindspore/mindspore/blob/master/mindspore/ccsrc/utils/anf_ir.proto) file.
\ No newline at end of file
TensorProto is defined in the [anf_ir.proto](https://gitee.com/mindspore/mindspore/blob/r0.7/mindspore/ccsrc/utils/anf_ir.proto) file.
[MindInsight](https://gitee.com/mindspore/mindinsight) is a visualized debugging and tuning component of MindSpore. MindInsight can be used to complete tasks such as training visualization, performance tuning, and precision tuning.
...
...
@@ -40,11 +40,11 @@ The training information collection function in MindSpore consists of training i
Training information collection APIs include:
- Training information collection API based on the summary operator. This API contains four summary operators, that is, the ScalarSummary operator for recording scalar data, the ImageSummary operator for recording image data, the HistogramSummary operator for recording parameter distribution histogram data, and the TensorSummary operator for recording tensor data. For details about the operators, see [Operator List](https://www.mindspore.cn/docs/en/master/operator_list.html).
- Training information collection API based on the summary operator. This API contains four summary operators, that is, the ScalarSummary operator for recording scalar data, the ImageSummary operator for recording image data, the HistogramSummary operator for recording parameter distribution histogram data, and the TensorSummary operator for recording tensor data. For details about the operators, see [Operator List](https://www.mindspore.cn/docs/en/r0.7/operator_list.html).
- Training information collection API based on the Python API. You can use the [SummaryRecord.add_value](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.train.html#mindspore.train.summary.SummaryRecord.add_value) method to collect training information in Python code.
- Training information collection API based on the Python API. You can use the [SummaryRecord.add_value](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.train.html#mindspore.train.summary.SummaryRecord.add_value) method to collect training information in Python code.
- Easy-to-use training information collection callback. The [SummaryCollector](https://www.mindspore.cn/api/en/master/api/python/mindspore/mindspore.train.html#mindspore.train.callback.SummaryCollector) callback function can be used to conveniently collect common training information to training logs.
- Easy-to-use training information collection callback. The [SummaryCollector](https://www.mindspore.cn/api/en/r0.7/api/python/mindspore/mindspore.train.html#mindspore.train.callback.SummaryCollector) callback function can be used to conveniently collect common training information to training logs.
The training information persistence module mainly includes a summary_record module used to manage a cache and a write_pool module used to process data in parallel and write data into a file. After the training information is made persistent, it is stored in the training log file (summary file).
This document describes how to seek help and support when you encounter problems in using MindSpore. The following flowchart shows the overall help-seeking process which starts from users encountering a problem in using MindSpore and ends with they finding a proper solution. Help-seeking methods are introduced based on the flowchart.
> You can also use [MindWizard Tool](https://gitee.com/mindspore/mindinsight/tree/master/mindinsight/wizard/) to quickly generate classic network scripts.
> You can also use [MindWizard Tool](https://gitee.com/mindspore/mindinsight/tree/r0.7/mindinsight/wizard/) to quickly generate classic network scripts.
## Pre-trained Models
*It refers to the released MindSpore version. The hardware platforms that support model training are CPU, GPU and Ascend. As shown in the table below, ✓ indicates that the pre-trained model run on the selected platform.
Domain | Sub Domain| Network | Dataset | CPU | GPU | Ascend | 0.5.0-beta*
A：目前正在开发Wide & Deep、DeepFM、NCF等推荐类模型，NLP领域已经支持Bert_NEZHA，正在开发MASS等模型，用户可根据场景需要改造为生成类网络，可以关注[MindSpore Model Zoo](https://gitee.com/mindspore/mindspore/tree/master/mindspore/model_zoo)。
A：目前正在开发Wide & Deep、DeepFM、NCF等推荐类模型，NLP领域已经支持Bert_NEZHA，正在开发MASS等模型，用户可根据场景需要改造为生成类网络，可以关注[MindSpore Model Zoo](https://gitee.com/mindspore/mindspore/tree/r0.7/mindspore/model_zoo)。
A：MindSpore当前支持CPU/GPU/Ascend /NPU。目前笔记本电脑或者有GPU的环境，都可以通过Docker镜像来试用。当前MindSpore Model Zoo中有部分模型已经支持GPU的训练和推理，其他模型也在不断地进行完善。在分布式并行训练方面，MindSpore当前支持GPU多卡训练。你可以通过[RoadMap](https://www.mindspore.cn/docs/zh-CN/master/roadmap.html)和项目[Release note](https://gitee.com/mindspore/mindspore/blob/master/RELEASE.md)获取最新信息。
A：MindSpore当前支持CPU/GPU/Ascend /NPU。目前笔记本电脑或者有GPU的环境，都可以通过Docker镜像来试用。当前MindSpore Model Zoo中有部分模型已经支持GPU的训练和推理，其他模型也在不断地进行完善。在分布式并行训练方面，MindSpore当前支持GPU多卡训练。你可以通过[RoadMap](https://www.mindspore.cn/docs/zh-CN/r0.7/roadmap.html)和项目[Release note](https://gitee.com/mindspore/mindspore/blob/r0.7/RELEASE.md)获取最新信息。
2. 业界其他开源框架数据可参考：[ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/ConvNets/resnet50v1.5)。
2. 业界其他开源框架数据可参考：[ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/r0.7/TensorFlow/Classification/ConvNets/resnet50v1.5)。
@@ -22,9 +22,9 @@ The Benchmark tool is used to perform benchmark testing on a MindSpore Lite mode
To use the Benchmark tool, you need to prepare the environment as follows:
- Compilation: Install compilation dependencies and perform compilation. The code of the Benchmark tool is stored in the `mindspore/lite/tools/benchmark` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/en/master/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/en/master/deploy.html#id5) in the deployment document.
- Compilation: Install compilation dependencies and perform compilation. The code of the Benchmark tool is stored in the `mindspore/lite/tools/benchmark` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/en/r0.7/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/en/r0.7/deploy.html#id5) in the deployment document.
- Run: Obtain the `Benchmark` tool and configure environment variables. For details, see [Output Description] (https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html#id4) in the deployment document.
- Run: Obtain the `Benchmark` tool and configure environment variables. For details, see [Output Description] (https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html#id4) in the deployment document.
@@ -23,9 +23,9 @@ Currently, the following input formats are supported: MindSpore, TensorFlow Lite
To use the MindSpore Lite model conversion tool, you need to prepare the environment as follows:
- Compilation: Install basic and additional compilation dependencies and perform compilation. The compilation version is x86_64. The code of the model conversion tool is stored in the `mindspore/lite/tools/converter` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html#id5) in the deployment document.
- Compilation: Install basic and additional compilation dependencies and perform compilation. The compilation version is x86_64. The code of the model conversion tool is stored in the `mindspore/lite/tools/converter` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html#id5) in the deployment document.
- Run: Obtain the `converter` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html#id4) in the deployment document.
- Run: Obtain the `converter` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html#id4) in the deployment document.
@@ -20,9 +20,9 @@ The TimeProfiler tool can be used to analyze the time consumption of forward inf
To use the TimeProfiler tool, you need to prepare the environment as follows:
- Compilation: Install compilation dependencies and perform compilation. The code of the TimeProfiler tool is stored in the `mindspore/lite/tools/time_profiler` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/en/master/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/en/master/deploy.html#id5) in the deployment document.
- Compilation: Install compilation dependencies and perform compilation. The code of the TimeProfiler tool is stored in the `mindspore/lite/tools/time_profiler` directory of the MindSpore source code. For details about the compilation operations, see the [Environment Requirements] (https://www.mindspore.cn/lite/docs/en/r0.7/deploy.html#id2) and [Compilation Example] (https://www.mindspore.cn/lite/docs/en/r0.7/deploy.html#id5) in the deployment document.
- Run: Obtain the `time_profiler` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html#id4) in the deployment document.
- Run: Obtain the `time_profiler` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html#id4) in the deployment document.
@@ -90,7 +90,7 @@ MindSpore Model Zoo中图像分类模型可[在此下载](#TODO)。
## 示例程序详细说明
本端侧图像分类Android示例程序分为JAVA层和JNI层，其中，JAVA层主要通过Android Camera 2 API实现摄像头获取图像帧，以及相应的图像处理等功能；JNI层在[Runtime](https://www.mindspore.cn/lite/tutorial/zh-CN/master/use/runtime.html)中完成模型推理的过程。
本端侧图像分类Android示例程序分为JAVA层和JNI层，其中，JAVA层主要通过Android Camera 2 API实现摄像头获取图像帧，以及相应的图像处理等功能；JNI层在[Runtime](https://www.mindspore.cn/lite/tutorial/zh-CN/r0.7/use/runtime.html)中完成模型推理的过程。
> 此处详细说明示例程序的JNI层实现，JAVA层运用Android Camera 2 API实现开启设备摄像头以及图像帧处理等功能，需读者具备一定的Android开发基础知识。
...
...
@@ -136,7 +136,7 @@ app
### 配置MindSpore Lite依赖项
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/lite/docs/zh-CN/master/deploy.html)生成`libmindspore-lite.so`库文件，或直接下载MindSpore Lite提供的已编译完成的AMR64、ARM32、x86等[软件包](#TODO)。
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/lite/docs/zh-CN/r0.7/deploy.html)生成`libmindspore-lite.so`库文件，或直接下载MindSpore Lite提供的已编译完成的AMR64、ARM32、x86等[软件包](#TODO)。
