- Based on **PaddleHub Serving**: Code path is "`./deploy/hubserving`". Please follow this tutorial.
- Based on **PaddleServing**: Code path is "`./deploy/pdserving`". Please refer to the [tutorial](../pdserving/readme_en.md) for usage.
# Service deployment based on PaddleHub Serving
The hubserving service deployment directory includes three service packages: detection, recognition, and two-stage series connection. Please select the corresponding service package to install and start service according to your needs. The directory is as follows:
...
...
@@ -37,7 +41,7 @@ SET PYTHONPATH=.
### 2. Download inference model
Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the ultra lightweight model of v1.1 is used, and the default detection model path is: `./inference/ch_ppocr_mobile_v1.1_det_infer/`, the default recognition model path is: `./inference/ch_ppocr_mobile_v1.1_rec_infer/`.
**The model path can be found and modified in `params.py`.** More models provided by PaddleOCR can be obtained from the [model library](../../doc/doc_en/models_list.md). You can also use models trained by yourself.
**The model path can be found and modified in `params.py`.** More models provided by PaddleOCR can be obtained from the [model library](../../doc/doc_en/models_list_en.md). You can also use models trained by yourself.
### 3. Install Service Module
PaddleOCR provides 3 kinds of service modules, install the required modules according to your needs.
- Based on **PaddleHub Serving**: Code path is "`./deploy/hubserving`". Please refer to the [tutorial](../hubserving/readme_en.md) for usage.
- Based on **PaddleServing**: Code path is "`./deploy/pdserving`". Please follow this tutorial.
# Service deployment based on Paddle Serving
This tutorial will introduce the detail steps of deploying PaddleOCR online prediction service based on [Paddle Serving](https://github.com/PaddlePaddle/Serving).
## Quick start service
### 1. Prepare the environment
Let's first install the relevant components of Paddle Serving. GPU is recommended for service deployment with Paddle Serving.
Executing the above command will download the `db_crnn_mobile` model, which is in different format with inference model. If you want to use other models for deployment, you can refer to the [tutorial](https://github.com/PaddlePaddle/Serving/blob/develop/doc/INFERENCE_TO_SERVING_CN.md) to convert your inference model to a model which is deployable for Paddle Serving.
We take `ch_rec_r34_vd_crnn` model as example. Download the inference model by executing the following command:
The pre-processing and post-processing process, can be found in the `preprocess` and `postprocess` function in `ocr_web_server.py` or `ocr_local_server.py`. The pre-processing/post-processing library for common CV models provided by `paddle_serving_app` is called.
You can modify the corresponding code as actual needs.
If you only want to start the detection service or the recognition service, execute the corresponding script reffering to the following table. Indicate the CPU or GPU is used in the start command parameters.
If you expect to load trained model and continue the training again, you can specify the parameter `Global.checkpoints` as the model path to be loaded.
The downloadable models provided by PaddleOCR include `inference model`, `trained model`, `pre-trained model` and `slim model`. The differences between the models are as follows:
|model type|model format|description|
|-|-|-|
|inference model|model、params|Used for reasoning based on Python prediction engine. [detail](./inference_en.md)|
|trained model / pre-trained model|\*.pdmodel、\*.pdopt、\*.pdparams|The checkpoints model saved in the training process, which stores the parameters of the model, mostly used for model evaluation and continuous training.|
|ch_ppocr_server_v1.1_det|General model, which is larger than the lightweight model, but achieved better performance|47.2M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar)|
<aname="Recognition"></a>
### 2. Text Recognition Model
<aname="Chinese"></a>
#### Chinese Recognition Model
|model name|description|model size|download|
|-|-|-|-|
|ch_ppocr_mobile_slim_v1.1_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|1.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)|
|ch_ppocr_mobile_v1.1_rec|Original lightweight model, supporting Chinese, English and number recognition|4.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar)|
|ch_ppocr_server_v1.1_rec|General model, supporting Chinese, English and number recognition|105M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar)|
**Note:** The `trained model` is finetuned on the `pre-trained model` with real data and synthsized vertical text data, which achieved better performance in real scene. The `pre-trained model` is directly trained on the full amount of real data and synthsized data, which is more suitable for finetune on your own dataset.
<aname="English"></a>
#### English Recognition Model
|model name|description|model size|download|
|-|-|-|-|
|en_ppocr_mobile_slim_v1.1_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|0.9M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/en/en_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/en/en_ppocr_mobile_v1.1_rec_quant_opt.nb)|
|en_ppocr_mobile_v1.1_rec|Original lightweight model, supporting English and number recognition|2.0M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/en/en_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/en/en_ppocr_mobile_v1.1_rec_train.tar)|
<aname="Multilingual"></a>
#### Multilingual Recognition Model（Updating...）
|model name|description|model size|download|
|-|-|-|-|
| french_ppocr_mobile_v1.1_rec |Lightweight model for French recognition|2.1M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_train.tar)|
| german_ppocr_mobile_v1.1_rec |German model for French recognition|2.1M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_train.tar)|
| korean_ppocr_mobile_v1.1_rec |Lightweight model for Korean recognition|3.4M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_train.tar)|
| japan_ppocr_mobile_v1.1_rec |Lightweight model for Japanese recognition|3.7M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_train.tar)|
