The structure of the prediction library is as follows:
```
inference_lite_lib.android.armv8/
|-- cxx C++ 预测库和头文件
| |-- include C++ 头文件
| | |-- paddle_api.h
| | |-- paddle_image_preprocess.h
| | |-- paddle_lite_factory_helper.h
| | |-- paddle_place.h
| | |-- paddle_use_kernels.h
| | |-- paddle_use_ops.h
| | `-- paddle_use_passes.h
| `-- lib C++预测库
| |-- libpaddle_api_light_bundled.a C++静态库
| `-- libpaddle_light_api_shared.so C++动态库
|-- java Java预测库
| |-- jar
| | `-- PaddlePredictor.jar
| |-- so
| | `-- libpaddle_lite_jni.so
| `-- src
|-- demo C++和Java示例代码
| |-- cxx C++ 预测库demo
| `-- java Java 预测库demo
```
## 4. Inference Model Optimization
Paddle Lite provides a variety of strategies to automatically optimize the original training model, including quantization, sub-graph fusion, hybrid scheduling, Kernel optimization and so on. In order to make the optimization process more convenient and easy to use, Paddle Lite provide opt tools to automatically complete the optimization steps and output a lightweight, optimal executable model.
If you use PaddleOCR 8.6M OCR model to deploy, you can directly download the optimized model.
|Introduction|Detection model|Recognition model|Paddle Lite branch |
|-|-|-|-|
|lightweight Chinese OCR optimized model|[Download](https://paddleocr.bj.bcebos.com/deploy/lite/ch_det_mv3_db_opt.nb)|[Download](https://paddleocr.bj.bcebos.com/deploy/lite/ch_rec_mv3_crnn_opt.nb)|develop|
If the model to be deployed is not in the above table, you need to follow the steps below to obtain the optimized model.
When the above code command is completed, there will be two more files `ch_det_mv3_db_opt.nb`,
`ch_rec_mv3_crnn_opt.nb` in the current directory, which is the converted model file.
## 5. Run optimized model on Phone
1. Prepare an Android phone with arm8. If the compiled prediction library and opt file are armv7, you need an arm7 phone and modify ARM_ABI = arm7 in the Makefile.
2. Make sure the phone is connected to the computer, open the USB debugging option of the phone, and select the file transfer mode.
If there is `device` output, it means the installation was successful.
4. Prepare optimized models, prediction library files, test images and dictionary files used. Create a new `ocr/` folder under the prediction library `inference_lite_lib.android.armv8/demo/cxx/`, and place all the files under `PaddleOCR/deploy/lite/` in the PaddleOCR repo except `readme.md` under the newly created ocr folder. Create a new debug folder under the ocr folder, and copy the C++ prediction library so file to the debug folder
Prepare the test image, taking `PaddleOCR/doc/imgs/11.jpg` as an example, copy the image file to the `demo/cxx/ocr/debug/` folder. The dictionary file for the Chinese super lightweight model is `PaddleOCR/ppocr/utils/ppocr_keys_v1.txt`, and copy it to the `demo/cxx/ocr/debug/` folder.
After the execution is completed, the following file formats will be in the ocr folder:
