forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

change model to inference modem

This commit is contained in:
WenmuZhou 2021-02-01 13:45:55 +08:00
parent 98ea077984
commit 6fc43d4b04
2 changed files with 21 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
deploy/lite/readme.md
View File

@ -123,15 +123,15 @@ cd build.opt/lite/api/
``` ```
# 【推荐】 下载PaddleOCR V2.0版本的中英文 inference模型 # 【推荐】 下载PaddleOCR V2.0版本的中英文 inference模型
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
# 转换V2.0检测模型 # 转换V2.0检测模型
./opt --model_file=./ch_ppocr_mobile_v2.0_det_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_det_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_det_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_det_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_det_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换V2.0识别模型 # 转换V2.0识别模型
./opt --model_file=./ch_ppocr_mobile_v2.0_rec_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_rec_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_rec_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_rec_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_rec_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换V2.0方向分类器模型 # 转换V2.0方向分类器模型
./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_opt --valid_targets=arm --optimize_out_type=naive_buffer
``` ```
@ -185,16 +185,16 @@ wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_s
``` ```
准备测试图像，以`PaddleOCR/doc/imgs/11.jpg`为例，将测试的图像复制到`demo/cxx/ocr/debug/`文件夹下。 准备测试图像，以`PaddleOCR/doc/imgs/11.jpg`为例，将测试的图像复制到`demo/cxx/ocr/debug/`文件夹下。
准备lite opt工具优化后的模型文件，比如使用`ch_ppocr_mobile_v2.0_det_slim_opt.nb，ch_ppocr_mobile_v2.0_rec_slim_opt.nb, ch_ppocr_mobile_v2.0_cls_slim_opt.nb`，模型文件放置在`demo/cxx/ocr/debug/`文件夹下。 准备lite opt工具优化后的模型文件，比如使用`ch_ppocr_mobile_v2.0_det_opt.nb，ch_ppocr_mobile_v2.0_rec_opt.nb, ch_ppocr_mobile_v2.0_cls_opt.nb`，模型文件放置在`demo/cxx/ocr/debug/`文件夹下。
执行完成后，ocr文件夹下将有如下文件格式： 执行完成后，ocr文件夹下将有如下文件格式：
``` ```
demo/cxx/ocr/ demo/cxx/ocr/
|-- debug/ |-- debug/
| |--ch_ppocr_mobile_v2.0_det_slim_opt.nb 优化后的检测模型文件 | |--ch_ppocr_mobile_v2.0_det_opt.nb 优化后的检测模型文件
| |--ch_ppocr_mobile_v2.0_rec_slim_opt.nb 优化后的识别模型文件 | |--ch_ppocr_mobile_v2.0_rec_opt.nb 优化后的识别模型文件
| |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb 优化后的文字方向分类器模型文件 | |--ch_ppocr_mobile_v2.0_cls_opt.nb 优化后的文字方向分类器模型文件
| |--11.jpg 待测试图像 | |--11.jpg 待测试图像
| |--ppocr_keys_v1.txt 中文字典文件 | |--ppocr_keys_v1.txt 中文字典文件
| |--libpaddle_light_api_shared.so C++预测库文件 | |--libpaddle_light_api_shared.so C++预测库文件
@ -248,7 +248,7 @@ use_direction_classify 0 # 是否使用方向分类器，0表示不使用，1
adb shell adb shell
cd /data/local/tmp/debug cd /data/local/tmp/debug
export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH
./ocr_db_crnn ch_ppocr_mobile_v2.0_det_slim_opt.nbb ch_ppocr_mobile_v2.0_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_slim_opt.nb ./11.jpg ppocr_keys_v1.txt ./ocr_db_crnn ch_ppocr_mobile_v2.0_det_opt.nbb ch_ppocr_mobile_v2.0_rec_opt.nb ch_ppocr_mobile_v2.0_cls_opt.nb ./11.jpg ppocr_keys_v1.txt
``` ```
如果对代码做了修改，则需要重新编译并push到手机上。 如果对代码做了修改，则需要重新编译并push到手机上。

20
deploy/lite/readme_en.md
View File

@ -124,16 +124,16 @@ The following takes the ultra-lightweight Chinese model of PaddleOCR as an examp
``` ```
# [Recommendation] Download the Chinese and English inference model of PaddleOCR V2.0 # [Recommendation] Download the Chinese and English inference model of PaddleOCR V2.0
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_slim_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar && tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
# Convert V2.0 detection model # Convert V2.0 detection model
./opt --model_file=./ch_ppocr_mobile_v2.0_det_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_det_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_det_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_det_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_det_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_det_opt --valid_targets=arm --optimize_out_type=naive_buffer
# 转换V2.0识别模型 # 转换V2.0识别模型
# Convert V2.0 recognition model # Convert V2.0 recognition model
./opt --model_file=./ch_ppocr_mobile_v2.0_rec_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_rec_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_rec_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_rec_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_rec_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_rec_opt --valid_targets=arm --optimize_out_type=naive_buffer
# Convert V2.0 angle classifier model # Convert V2.0 angle classifier model
./opt --model_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_slim_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_slim_opt --valid_targets=arm --optimize_out_type=naive_buffer ./opt --model_file=./ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel --param_file=./ch_ppocr_mobile_v2.0_cls_infer/inference.pdiparams --optimize_out=./ch_ppocr_mobile_v2.0_cls_opt --valid_targets=arm --optimize_out_type=naive_buffer
``` ```
@ -194,9 +194,9 @@ The structure of the OCR demo is as follows after the above command is executed:
``` ```
demo/cxx/ocr/ demo/cxx/ocr/
|-- debug/ |-- debug/
| |--ch_ppocr_mobile_v2.0_det_slim_opt.nb Detection model | |--ch_ppocr_mobile_v2.0_det_opt.nb Detection model
| |--ch_ppocr_mobile_v2.0_rec_slim_opt.nb Recognition model | |--ch_ppocr_mobile_v2.0_rec_opt.nb Recognition model
| |--ch_ppocr_mobile_v2.0_cls_slim_opt.nb Text direction classification model | |--ch_ppocr_mobile_v2.0_cls_opt.nb Text direction classification model
| |--11.jpg Image for OCR | |--11.jpg Image for OCR
| |--ppocr_keys_v1.txt Dictionary file | |--ppocr_keys_v1.txt Dictionary file
| |--libpaddle_light_api_shared.so C++ .so file | |--libpaddle_light_api_shared.so C++ .so file
@ -248,7 +248,7 @@ After the above steps are completed, you can use adb to push the file to the pho
adb shell adb shell
cd /data/local/tmp/debug cd /data/local/tmp/debug
export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH
./ocr_db_crnn ch_ppocr_mobile_v2.0_det_slim_opt.nbb ch_ppocr_mobile_v2.0_rec_slim_opt.nb ch_ppocr_mobile_v2.0_cls_slim_opt.nb ./11.jpg ppocr_keys_v1.txt ./ocr_db_crnn ch_ppocr_mobile_v2.0_det_opt.nbb ch_ppocr_mobile_v2.0_rec_opt.nb ch_ppocr_mobile_v2.0_cls_opt.nb ./11.jpg ppocr_keys_v1.txt
``` ```
If you modify the code, you need to recompile and push to the phone. If you modify the code, you need to recompile and push to the phone.