Skip to content

P
PaddleOCR

weixin_41840029 / PaddleOCR
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleOCR

通知 1
Star 1
Fork 0
P
PaddleOCR
提交 3d11aba9 编写于 作者: L LDOUBLEV
浏览文件
操作

fix lite doc, test=document_fix

上级 f4d826a5
隐藏空白更改
内联 并排
Showing with 38 addition and 19 deletion
deploy/lite/ocr_db_crnn.cc
浏览文件 @ 3d11aba9
...@@ -290,7 +290,7 @@ RunDetModel(std::shared_ptr<PaddlePredictor> predictor, cv::Mat img, ...@@ -290,7 +290,7 @@ RunDetModel(std::shared_ptr<PaddlePredictor> predictor, cv::Mat img,
cv::Mat bit_map; cv::Mat bit_map;
cv::threshold(cbuf_map, bit_map, threshold, maxvalue, cv::THRESH_BINARY); cv::threshold(cbuf_map, bit_map, threshold, maxvalue, cv::THRESH_BINARY);
cv::Mat dilation_map; cv::Mat dilation_map;
cv::Mat dila_ele = cv::getStructuringElement(cv::MORPH_RECT, cv::Size(2,2)); cv::Mat dila_ele = cv::getStructuringElement(cv::MORPH_RECT, cv::Size(2, 2));
cv::dilate(bit_map, dilation_map, dila_ele); cv::dilate(bit_map, dilation_map, dila_ele);
auto boxes = BoxesFromBitmap(pred_map, dilation_map, Config); auto boxes = BoxesFromBitmap(pred_map, dilation_map, Config);
...@@ -366,7 +366,8 @@ std::map<std::string, double> LoadConfigTxt(std::string config_path) { ...@@ -366,7 +366,8 @@ std::map<std::string, double> LoadConfigTxt(std::string config_path) {
int main(int argc, char **argv) { int main(int argc, char **argv) {
if (argc < 5) { if (argc < 5) {
std::cerr << "[ERROR] usage: " << argv[0] std::cerr << "[ERROR] usage: " << argv[0]
<< " det_model_file rec_model_file image_path\n"; << " det_model_file cls_model_file rec_model_file image_path "
"charactor_dict\n";
exit(1); exit(1);
} }
std::string det_model_file = argv[1]; std::string det_model_file = argv[1];
......
deploy/lite/readme.md
浏览文件 @ 3d11aba9
...@@ -83,7 +83,7 @@ Paddle-Lite 提供了多种策略来自动优化原始的模型，其中包括 ...@@ -83,7 +83,7 @@ Paddle-Lite 提供了多种策略来自动优化原始的模型，其中包括
|模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本| |模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本|
|-|-|-|-|-|-|-| |-|-|-|-|-|-|-|
|V1.1|超轻量中文OCR 移动端模型|3.0M|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_cls_quant_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)|develop| |V1.1|超轻量中文OCR 移动端模型|3.5M|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_cls_quant_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)|develop|
|V1.0|轻量级中文OCR 移动端模型|8.6M|[下载地址](https://paddleocr.bj.bcebos.com/deploy/lite/ch_det_mv3_db_opt.nb)|---|[下载地址](https://paddleocr.bj.bcebos.com/deploy/lite/ch_rec_mv3_crnn_opt.nb)|develop| |V1.0|轻量级中文OCR 移动端模型|8.6M|[下载地址](https://paddleocr.bj.bcebos.com/deploy/lite/ch_det_mv3_db_opt.nb)|---|[下载地址](https://paddleocr.bj.bcebos.com/deploy/lite/ch_rec_mv3_crnn_opt.nb)|develop|
注意：V1.1 3.0M 轻量模型是使用PaddleSlim优化后的，需要配合Paddle-Lite最新预测库使用。 注意：V1.1 3.0M 轻量模型是使用PaddleSlim优化后的，需要配合Paddle-Lite最新预测库使用。
...@@ -123,18 +123,27 @@ cd build.opt/lite/api/ ...@@ -123,18 +123,27 @@ cd build.opt/lite/api/
下面以PaddleOCR的超轻量中文模型为例，介绍使用编译好的opt文件完成inference模型到Paddle-Lite优化模型的转换。 下面以PaddleOCR的超轻量中文模型为例，介绍使用编译好的opt文件完成inference模型到Paddle-Lite优化模型的转换。
``` ```
# 下载PaddleOCR的超轻量文inference模型，并解压 # 可以下载PaddleOCR V1.1版本的inference模型，V1.1比1.0效果更好，模型大小更小
wget https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar && tar xf ch_ppocr_mobile_v1.1_det_prune_infer.tar
wget https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar && tar xf ch_ppocr_mobile_v1.1_rec_quant_infer.tar
# 转换V1.1检测模型
./opt --model_file=./ch_ppocr_mobile_v1.1_det_prune_infer/model --param_file=./ch_ppocr_mobile_v1.1_det_prune_infer/params --optimize_out=./ch_ppocr_mobile_v1.1_det_prune_opt --valid_targets=arm
# 转换V1.1识别模型
./opt --model_file=./ch_ppocr_mobile_v1.1_rec_quant_infer/model --param_file=./ch_ppocr_mobile_v1.1_rec_quant_infer/params --optimize_out=./ch_ppocr_mobile_v1.1_rec_quant_opt --valid_targets=arm
# 或下载使用PaddleOCR的V1.0超轻量文inference模型，并解压
wget https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar && tar xf ch_det_mv3_db_infer.tar wget https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar && tar xf ch_det_mv3_db_infer.tar
wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar xf ch_rec_mv3_crnn_infer.tar wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar xf ch_rec_mv3_crnn_infer.tar
# 转换V1.0检测模型
# 转换检测模型
./opt --model_file=./ch_det_mv3_db/model --param_file=./ch_det_mv3_db/params --optimize_out_type=naive_buffer --optimize_out=./ch_det_mv3_db_opt --valid_targets=arm ./opt --model_file=./ch_det_mv3_db/model --param_file=./ch_det_mv3_db/params --optimize_out_type=naive_buffer --optimize_out=./ch_det_mv3_db_opt --valid_targets=arm
# 转换V1.0识别模型
# 转换识别模型
./opt --model_file=./ch_rec_mv3_crnn/model --param_file=./ch_rec_mv3_crnn/params --optimize_out_type=naive_buffer --optimize_out=./ch_rec_mv3_crnn_opt --valid_targets=arm ./opt --model_file=./ch_rec_mv3_crnn/model --param_file=./ch_rec_mv3_crnn/params --optimize_out_type=naive_buffer --optimize_out=./ch_rec_mv3_crnn_opt --valid_targets=arm
``` ```
转换成功后，当前目录下会多出`ch_det_mv3_db_opt.nb`, `ch_rec_mv3_crnn_opt.nb`结尾的文件，即是转换成功的模型文件。 # 转换V1.1检测模型
转换成功后，当前目录下会多出`.nb`结尾的文件，即是转换成功的模型文件。
注意：使用paddle-lite部署时，需要使用opt工具优化后的模型。 opt 转换的输入模型是paddle保存的inference模型 注意：使用paddle-lite部署时，需要使用opt工具优化后的模型。 opt 转换的输入模型是paddle保存的inference模型
...@@ -184,15 +193,16 @@ wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar ...@@ -184,15 +193,16 @@ wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar
``` ```
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_det_mv3_db_opt.nb，ch_rec_mv3_crnn_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_v1.1_det_prune_opt.nb，ch_ppocr_mobile_v1.1_rec_quant_opt.nb, ch_ppocr_mobile_cls_quant_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_det_mv3_db_opt.nb 优化后的检测模型文件 | |--ch_ppocr_mobile_v1.1_det_prune_opt.nb 优化后的检测模型文件
| |--ch_rec_mv3_crnn_opt.nb 优化后的识别模型文件 | |--ch_ppocr_mobile_v1.1_rec_quant_opt.nb 优化后的识别模型文件
| |--ch_ppocr_mobile_cls_quant_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 字典文件 | |--ppocr_keys_v1.txt 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
...@@ -223,7 +233,7 @@ demo/cxx/ocr/ ...@@ -223,7 +233,7 @@ demo/cxx/ocr/
adb shell adb shell
cd /data/local/tmp/debug cd /data/local/tmp/debug
export LD_LIBRARY_PATH=/data/local/tmp/debug:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=/data/local/tmp/debug:$LD_LIBRARY_PATH
./ocr_db_crnn ch_det_mv3_db_opt.nb ch_rec_mv3_crnn_opt.nb ./11.jpg ppocr_keys_v1.txt ./ocr_db_crnn ch_ppocr_mobile_v1.1_det_prune_opt.nb ch_ppocr_mobile_v1.1_rec_quant_opt.nb ch_ppocr_mobile_cls_quant_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。
......
deploy/lite/readme_en.md
浏览文件 @ 3d11aba9
...@@ -66,7 +66,7 @@ If you use PaddleOCR 8.6M OCR model to deploy, you can directly download the opt ...@@ -66,7 +66,7 @@ If you use PaddleOCR 8.6M OCR model to deploy, you can directly download the opt
|Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle Lite branch | |Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle Lite branch |
|-|-|-|-|-|-| |-|-|-|-|-|-|
|V1.1|extra-lightweight chinese OCR optimized model|3.0M|[Download](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)|[Download](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_cls_quant_opt.nb)|[Download](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)|develop| |V1.1|extra-lightweight chinese OCR optimized model|3.5M|[Download](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)|[Download](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_cls_quant_opt.nb)|[Download](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)|develop|
|V1.0|lightweight Chinese OCR optimized model|8.6M|[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| |V1.0|lightweight Chinese OCR optimized model|8.6M|[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. If the model to be deployed is not in the above table, you need to follow the steps below to obtain the optimized model.
...@@ -86,6 +86,14 @@ The `opt` can optimize the inference model saved by paddle.io.save_inference_mod ...@@ -86,6 +86,14 @@ The `opt` can optimize the inference model saved by paddle.io.save_inference_mod
The usage of opt is as follows： The usage of opt is as follows：
``` ```
# V1.1 is better than V1.0. steps for convert V1.1 model to nb file are as follows
wget https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar && tar xf ch_ppocr_mobile_v1.1_det_prune_infer.tar
wget https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar && tar xf ch_ppocr_mobile_v1.1_rec_quant_infer.tar
./opt --model_file=./ch_ppocr_mobile_v1.1_det_prune_infer/model --param_file=./ch_ppocr_mobile_v1.1_det_prune_infer/params --optimize_out=./ch_ppocr_mobile_v1.1_det_prune_opt --valid_targets=arm
./opt --model_file=./ch_ppocr_mobile_v1.1_rec_quant_infer/model --param_file=./ch_ppocr_mobile_v1.1_rec_quant_infer/params --optimize_out=./ch_ppocr_mobile_v1.1_rec_quant_opt --valid_targets=arm
# or use V1.0 model
wget https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar && tar xf ch_det_mv3_db_infer.tar wget https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar && tar xf ch_det_mv3_db_infer.tar
wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar xf ch_rec_mv3_crnn_infer.tar wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar xf ch_rec_mv3_crnn_infer.tar
...@@ -94,8 +102,7 @@ wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar ...@@ -94,8 +102,7 @@ wget https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar && tar
``` ```
When the above code command is completed, there will be two more files `ch_det_mv3_db_opt.nb`, When the above code command is completed, there will be two more files `.nb` in the current directory, which is the converted model file.
`ch_rec_mv3_crnn_opt.nb` in the current directory, which is the converted model file.
## 5. Run optimized model on Phone ## 5. Run optimized model on Phone
...@@ -154,8 +161,9 @@ The structure of the OCR demo is as follows after the above command is executed: ...@@ -154,8 +161,9 @@ The structure of the OCR demo is as follows after the above command is executed:
``` ```
demo/cxx/ocr/ demo/cxx/ocr/
|-- debug/ |-- debug/
| |--ch_det_mv3_db_opt.nb Detection model | |--ch_ppocr_mobile_v1.1_det_prune_opt.nb Detection model
| |--ch_rec_mv3_crnn_opt.nb Recognition model | |--ch_ppocr_mobile_v1.1_rec_quant_opt.nb Recognition model
| |--ch_ppocr_mobile_cls_quant_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
...@@ -181,7 +189,7 @@ adb shell ...@@ -181,7 +189,7 @@ adb shell
cd /data/local/tmp/debug cd /data/local/tmp/debug
export LD_LIBRARY_PATH=/data/local/tmp/debug:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=/data/local/tmp/debug:$LD_LIBRARY_PATH
# run model # run model
./ocr_db_crnn ch_det_mv3_db_opt.nb ch_rec_mv3_crnn_opt.nb ./11.jpg ppocr_keys_v1.txt ./ocr_db_crnn ch_ppocr_mobile_v1.1_det_prune_opt.nb ch_ppocr_mobile_v1.1_rec_quant_opt.nb ch_ppocr_mobile_cls_quant_opt.nb ./11.jpg ppocr_keys_v1.txt
``` ```
The outputs are as follows: The outputs are as follows:
......
Markdown is supported
0% 或 .
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 或