Please prepare your environment referring to [prepare the environment](./environment_en.md) and [clone the repo](./clone_en.md).
<aname="3"></a>
## 3. Model Training / Evaluation / Prediction
Please refer to [text detection training tutorial](./detection_en.md). PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
<aname="4"></a>
## 4. Inference and Deployment
<aname="4-1"></a>
### 4.1 Python Inference
#### (1). Quadrangle text detection model (ICDAR2015)
First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)), you can use the following command to convert:
The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
#### (2). Curved text detection model (Total-Text)
First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the Total-Text English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)), you can use the following command to convert:
For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`, run the following command:
The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
**Note**: SAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases.
<aname="4-2"></a>
### 4.2 C++ Inference
Not supported
<aname="4-3"></a>
### 4.3 Serving
Not supported
<aname="4-4"></a>
### 4.4 More
Not supported
<aname="5"></a>
## 5. FAQ
## Citation
```bibtex
@inproceedings{wang2019single,
title={A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning},
author={Wang, Pengfei and Zhang, Chengquan and Qi, Fei and Huang, Zuming and En, Mengyi and Han, Junyu and Liu, Jingtuo and Ding, Errui and Shi, Guangming},
booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
-[3. Model Training / Evaluation / Prediction](#3)
-[3.1 Training](#3-1)
-[3.2 Evaluation](#3-2)
-[3.3 Prediction](#3-3)
-[4. Inference and Deployment](#4)
-[4.1 Python Inference](#4-1)
-[4.2 C++ Inference](#4-2)
-[4.3 Serving](#4-3)
-[4.4 More](#4-4)
-[5. FAQ](#5)
<aname="1"></a>
## 1. Introduction
Paper:
> [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://arxiv.org/abs/1811.00751)
> Hui Li, Peng Wang, Chunhua Shen, Guyu Zhang
> AAAI, 2019
Using MJSynth and SynthText two text recognition datasets for training, and evaluating on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE datasets, the algorithm reproduction effect is as follows:
Note:In addition to using the two text recognition datasets MJSynth and SynthText, [SynthAdd](https://pan.baidu.com/share/init?surl=uV0LtoNmcxbO-0YA7Ch4dg) data (extraction code: 627x), and some real data are used in training, the specific data details can refer to the paper.
<aname="2"></a>
## 2. Environment
Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code.
<aname="3"></a>
## 3. Model Training / Evaluation / Prediction
Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**.
Training:
Specifically, after the data preparation is completed, the training can be started. The training command is as follows:
```
#Single GPU training (long training period, not recommended)
First, the model saved during the SAR text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) ), you can use the following command to convert:
-[3. Model Training / Evaluation / Prediction](#3)
-[3.1 Training](#3-1)
-[3.2 Evaluation](#3-2)
-[3.3 Prediction](#3-3)
-[4. Inference and Deployment](#4)
-[4.1 Python Inference](#4-1)
-[4.2 C++ Inference](#4-2)
-[4.3 Serving](#4-3)
-[4.4 More](#4-4)
-[5. FAQ](#5)
<aname="1"></a>
## 1. Introduction
Paper:
> [Towards Accurate Scene Text Recognition with Semantic Reasoning Networks](https://arxiv.org/abs/2003.12294#)
> Deli Yu, Xuan Li, Chengquan Zhang, Junyu Han, Jingtuo Liu, Errui Ding
> CVPR,2020
Using MJSynth and SynthText two text recognition datasets for training, and evaluating on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE datasets, the algorithm reproduction effect is as follows:
Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code.
<aname="3"></a>
## 3. Model Training / Evaluation / Prediction
Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**.
Training:
Specifically, after the data preparation is completed, the training can be started. The training command is as follows:
```
#Single GPU training (long training period, not recommended)
First, the model saved during the SRN text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) ), you can use the following command to convert:
-**Introduction**： A total of 45w Chinese street view images, including 5w (2w test + 3w training) fully labeled data (text coordinates + text content), 40w weakly labeled data (text content only), as shown in the following figure:
-**Introduction**： A total of 45w Chinese street view images, including 5w (2w test + 3w training) fully labeled data (text coordinates + text content), 40w weakly labeled data (text content only), as shown in the following figure:
@@ -25,7 +25,7 @@ In addition to opensource data, users can also use synthesis tools to synthesize
...
@@ -25,7 +25,7 @@ In addition to opensource data, users can also use synthesis tools to synthesize
#### 2. ICDAR2017-RCTW-17
#### 2. ICDAR2017-RCTW-17
-**Data sources**：https://rctw.vlrlab.net/
-**Data sources**：https://rctw.vlrlab.net/
-**Introduction**：It contains 12000 + images, most of them are collected in the wild through mobile camera. Some are screenshots. These images show a variety of scenes, including street views, posters, menus, indoor scenes and screenshots of mobile applications.
-**Introduction**：It contains 12000 + images, most of them are collected in the wild through mobile camera. Some are screenshots. These images show a variety of scenes, including street views, posters, menus, indoor scenes and screenshots of mobile applications.
-**Introduction**：A total of 290000 pictures are included, of which 210000 are used as training sets (with labels) and 80000 are used as test sets (without labels). The dataset is collected from the Chinese street view, and is formed by by cutting out the text line area (such as shop signs, landmarks, etc.) in the street view picture. All the images are preprocessed: by using affine transform, the text area is proportionally mapped to a picture with a height of 48 pixels, as shown in the figure:
-**Introduction**：A total of 290000 pictures are included, of which 210000 are used as training sets (with labels) and 80000 are used as test sets (without labels). The dataset is collected from the Chinese street view, and is formed by by cutting out the text line area (such as shop signs, landmarks, etc.) in the street view picture. All the images are preprocessed: by using affine transform, the text area is proportionally mapped to a picture with a height of 48 pixels, as shown in the figure:
- 5990 characters including Chinese characters, English letters, numbers and punctuation（Characters set: https://github.com/YCG09/chinese_ocr/blob/master/train/char_std_5990.txt ）
- 5990 characters including Chinese characters, English letters, numbers and punctuation（Characters set: https://github.com/YCG09/chinese_ocr/blob/master/train/char_std_5990.txt ）
- Each sample is fixed with 10 characters, and the characters are randomly intercepted from the sentences in the corpus
- Each sample is fixed with 10 characters, and the characters are randomly intercepted from the sentences in the corpus
-**Introduction**：It includes 10166 images, 5603 in training sets and 4563 in test sets. It is composed of three parts: total text, scut-ctw1500 and Baidu curved scene text, including text with various shapes such as horizontal, multi-directional and curved.
-**Introduction**：It includes 10166 images, 5603 in training sets and 4563 in test sets. It is composed of three parts: total text, scut-ctw1500 and Baidu curved scene text, including text with various shapes such as horizontal, multi-directional and curved.
-**Data Introduction**: The FUNSD dataset is a dataset for form comprehension. It contains 199 real, fully annotated scanned images, including market reports, advertisements, and academic reports, etc., and is divided into 149 50 training sets and 50 test sets. The FUNSD dataset is suitable for many types of DocVQA tasks, such as field-level entity classification, field-level entity connection, etc. Part of the image and the annotation box visualization are shown below:
In the figure, the orange area represents `header`, the light blue area represents `question`, the green area represents `answer`, and the pink area represents `other`.
-**Data introduction**: XFUND is a multilingual form comprehension dataset, which contains form data in 7 different languages, and all are manually annotated in the form of key-value pairs. The data for each language contains 199 form data, which are divided into 149 training sets and 50 test sets. Part of the image and the annotation box visualization are shown below:
@@ -9,7 +9,7 @@ Here we have sorted out the commonly used handwritten OCR dataset datasets, whic
...
@@ -9,7 +9,7 @@ Here we have sorted out the commonly used handwritten OCR dataset datasets, whic
-**Data introduction**:
-**Data introduction**:
* It includes online and offline handwritten data,`HWDB1.0~1.2` has totally 3895135 handwritten single character samples, which belong to 7356 categories (7185 Chinese characters and 171 English letters, numbers and symbols);`HWDB2.0~2.2` has totally 5091 pages of images, which are divided into 52230 text lines and 1349414 words. All text and text samples are stored as grayscale images. Some sample words are shown below.
* It includes online and offline handwritten data,`HWDB1.0~1.2` has totally 3895135 handwritten single character samples, which belong to 7356 categories (7185 Chinese characters and 171 English letters, numbers and symbols);`HWDB2.0~2.2` has totally 5091 pages of images, which are divided into 52230 text lines and 1349414 words. All text and text samples are stored as grayscale images. Some sample words are shown below.
-**使用建议**:Data for single character, white background, can form a large number of text lines for training. White background can be processed into transparent state, which is convenient to add various backgrounds. For the case of semantic needs, it is suggested to extract single character from real corpus to form text lines.
-**使用建议**:Data for single character, white background, can form a large number of text lines for training. White background can be processed into transparent state, which is convenient to add various backgrounds. For the case of semantic needs, it is suggested to extract single character from real corpus to form text lines.
...
@@ -22,7 +22,7 @@ Here we have sorted out the commonly used handwritten OCR dataset datasets, whic
...
@@ -22,7 +22,7 @@ Here we have sorted out the commonly used handwritten OCR dataset datasets, whic
-**Data introduction**: NIST19 dataset is suitable for handwritten document and character recognition model training. It is extracted from the handwritten sample form of 3600 authors and contains 810000 character images in total. Nine of them are shown below.
-**Data introduction**: NIST19 dataset is suitable for handwritten document and character recognition model training. It is extracted from the handwritten sample form of 3600 authors and contains 810000 character images in total. Nine of them are shown below.
The image annotation after **json.dumps()** encoding is a list containing multiple dictionaries.
The `points` in the dictionary represent the coordinates (x, y) of the four points of the text box, arranged clockwise from the point at the upper left corner.
`transcription` represents the text of the current text box. **When its content is "###" it means that the text box is invalid and will be skipped during training.**
If you want to train PaddleOCR on other datasets, please build the annotation file according to the above format.
### 1.2 Public dataset
| dataset | Image download link | PaddleOCR format annotation download link |
| ctw1500 | https://paddleocr.bj.bcebos.com/dataset/ctw1500.zip | Included in the downloaded image zip |
| total text | https://paddleocr.bj.bcebos.com/dataset/total_text.tar | Included in the downloaded image zip |
#### 1.2.1 ICDAR 2015
The icdar2015 dataset contains train set which has 1000 images obtained with wearable cameras and test set which has 500 images obtained with wearable cameras. The icdar2015 dataset can be downloaded from the link in the table above. Registration is required for downloading.
After registering and logging in, download the part marked in the red box in the figure below. And, the content downloaded by `Training Set Images` should be saved as the folder `icdar_c4_train_imgs`, and the content downloaded by `Test Set Images` is saved as the folder `ch4_test_images`
Decompress the downloaded dataset to the working directory, assuming it is decompressed under PaddleOCR/train_data/. Then download the PaddleOCR format annotation file from the table above.
PaddleOCR also provides a data format conversion script, which can convert the official website label to the PaddleOCR format. The data conversion tool is in `ppocr/utils/gen_label.py`, here is the training set as an example:
```
# Convert the label file downloaded from the official website to train_icdar2015_label.txt
└─ icdar_c4_train_imgs/ Training data of icdar dataset
└─ ch4_test_images/ Testing data of icdar dataset
└─ train_icdar2015_label.txt Training annotation of icdar dataset
└─ test_icdar2015_label.txt Test annotation of icdar dataset
```
## 2. Text recognition
### 2.1 PaddleOCR text recognition format annotation
The text recognition algorithm in PaddleOCR supports two data formats:
-`lmdb` is used to train data sets stored in lmdb format, use [lmdb_dataset.py](../../../ppocr/data/lmdb_dataset.py) to load;
-`common dataset` is used to train data sets stored in text files, use [simple_dataset.py](../../../ppocr/data/simple_dataset.py) to load.
If you want to use your own data for training, please refer to the following to organize your data.
- Training set
It is recommended to put the training images in the same folder, and use a txt file (rec_gt_train.txt) to store the image path and label. The contents of the txt file are as follows:
* Note: by default, the image path and image label are split with \t, if you use other methods to split, it will cause training error
```
" Image file name Image annotation "
train_data/rec/train/word_001.jpg 简单可依赖
train_data/rec/train/word_002.jpg 用科技让复杂的世界更简单
...
```
The final training set should have the following file structure:
```
|-train_data
|-rec
|- rec_gt_train.txt
|- train
|- word_001.png
|- word_002.jpg
|- word_003.jpg
| ...
```
- Test set
Similar to the training set, the test set also needs to be provided a folder containing all images (test) and a rec_gt_test.txt. The structure of the test set is as follows:
```
|-train_data
|-rec
|-ic15_data
|- rec_gt_test.txt
|- test
|- word_001.jpg
|- word_002.jpg
|- word_003.jpg
| ...
```
### 2.2 Public dataset
| dataset | Image download link | PaddleOCR format annotation download link |
|---|---|---|
| en benchmark(MJ, SJ, IIIT, SVT, IC03, IC13, IC15, SVTP, and CUTE.) | [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) | LMDB format, which can be loaded directly with [lmdb_dataset.py](../../../ppocr/data/lmdb_dataset.py) |
| Multilingual datasets |[Baidu network disk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) Extraction code: frgi <br>[google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view) | Included in the downloaded image zip |
#### 2.1 ICDAR 2015
The ICDAR 2015 dataset can be downloaded from the link in the table above for quick validation. The lmdb format dataset required by en benchmark can also be downloaded from the table above.
Then download the PaddleOCR format annotation file from the table above.
PaddleOCR also provides a data format conversion script, which can convert the ICDAR official website label to the data format supported by PaddleOCR. The data conversion tool is in `ppocr/utils/gen_label.py`, here is the training set as an example:
```
# Convert the label file downloaded from the official website to rec_gt_label.txt
The data format is as follows, (a) is the original picture, (b) is the Ground Truth text file corresponding to each picture:
## 3. Data storage path
The default storage path for PaddleOCR training data is `PaddleOCR/train_data`, if you already have a dataset on your disk, just create a soft link to the dataset directory:
-[2. TAL Table Recognition Competition Dataset](#2-tal-table-recognition-competition-dataset)
Here are the commonly used table recognition datasets, which are being updated continuously. Welcome to contribute datasets~
## Dataset Summary
| dataset | Image download link | PPOCR format annotation download link |
|---|---|---|
| PubTabNet |https://github.com/ibm-aur-nlp/PubTabNet| jsonl format, which can be loaded directly with [pubtab_dataset.py](../../../ppocr/data/pubtab_dataset.py) |
| TAL Table Recognition Competition Dataset |https://ai.100tal.com/dataset| jsonl format, which can be loaded directly with [pubtab_dataset.py](../../../ppocr/data/pubtab_dataset.py) |
## 1. PubTabNet
-**Data Introduction**：The training set of the PubTabNet dataset contains 500,000 images and the validation set contains 9000 images. Part of the image visualization is shown below.
-**illustrate**：When using this dataset, the [CDLA-Permissive](https://cdla.io/permissive-1-0/) protocol is required.
## 2. TAL Table Recognition Competition Dataset
-**Data Introduction**：The training set of the TAL table recognition competition dataset contains 16,000 images. The validation set does not give trainable annotations.
@@ -59,7 +59,7 @@ Here we have sorted out the commonly used vertical multi-language OCR dataset da
...
@@ -59,7 +59,7 @@ Here we have sorted out the commonly used vertical multi-language OCR dataset da
-**Data introduction**: This is a toolkit for data synthesis. You can output captcha images according to the input text. Use the toolkit to generate several demo images as follows.
-**Data introduction**: This is a toolkit for data synthesis. You can output captcha images according to the input text. Use the toolkit to generate several demo images as follows.
-**Download address**: The dataset is generated and has no download address.
-**Download address**: The dataset is generated and has no download address.
*[2.7 Training on other platform(Windows/macOS/Linux DCU)](#27)
-[3. Evaluation and Test](#3-evaluation-and-test)
-[3. Evaluation and Test](#3-evaluation-and-test)
*[3.1 Evaluation](#31-evaluation)
-[3.1 Evaluation](#31-evaluation)
*[3.2 Test](#32-test)
-[3.2 Test](#32-test)
-[4. Inference](#4-inference)
-[4. Inference](#4-inference)
-[5. FAQ](#2-faq)
-[5. FAQ](#5-faq)
## 1. Data and Weights Preparation
## 1. Data and Weights Preparation
### 1.1 Data Preparation
### 1.1 Data Preparation
The icdar2015 dataset contains train set which has 1000 images obtained with wearable cameras and test set which has 500 images obtained with wearable cameras. The icdar2015 can be obtained from [official website](https://rrc.cvc.uab.es/?ch=4&com=downloads). Registration is required for downloading.
To prepare datasets, refer to [ocr_datasets](./dataset/ocr_datasets_en.md) .
After registering and logging in, download the part marked in the red box in the figure below. And, the content downloaded by `Training Set Images` should be saved as the folder `icdar_c4_train_imgs`, and the content downloaded by `Test Set Images` is saved as the folder `ch4_test_images`
Decompress the downloaded dataset to the working directory, assuming it is decompressed under PaddleOCR/train_data/. In addition, PaddleOCR organizes many scattered annotation files into two separate annotation files for train and test respectively, which can be downloaded by wget:
The image annotation after **json.dumps()** encoding is a list containing multiple dictionaries.
The `points` in the dictionary represent the coordinates (x, y) of the four points of the text box, arranged clockwise from the point at the upper left corner.
`transcription` represents the text of the current text box. **When its content is "###" it means that the text box is invalid and will be skipped during training.**
If you want to train PaddleOCR on other datasets, please build the annotation file according to the above format.
### 1.2 Download Pre-trained Model
### 1.2 Download Pre-trained Model
...
@@ -175,11 +140,44 @@ After adding the four-part modules of the network, you only need to configure th
...
@@ -175,11 +140,44 @@ After adding the four-part modules of the network, you only need to configure th
**NOTE**: More details about replace Backbone and other mudule can be found in [doc](add_new_algorithm_en.md).
**NOTE**: More details about replace Backbone and other mudule can be found in [doc](add_new_algorithm_en.md).
### 2.4 Mixed Precision Training
### 2.4 Training with knowledge distillation
If you want to speed up your training further, you can use [Auto Mixed Precision Training](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/01_paddle2.0_introduction/basic_concept/amp_cn.html), taking a single machine and a single gpu as an example, the commands are as follows:
During multi-machine multi-gpu training, use the `--ips` parameter to set the used machine IP address, and the `--gpus` parameter to set the used GPU ID:
**Note:** When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. In addition, training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`.
### 2.6 Training with knowledge distillation
Knowledge distillation is supported in PaddleOCR for text detection training process. For more details, please refer to [doc](./knowledge_distillation_en.md).
Knowledge distillation is supported in PaddleOCR for text detection training process. For more details, please refer to [doc](./knowledge_distillation_en.md).
### 2.7 Training on other platform(Windows/macOS/Linux DCU)
- Windows GPU/CPU
The Windows platform is slightly different from the Linux platform:
Windows platform only supports `single gpu` training and inference, specify GPU for training `set CUDA_VISIBLE_DEVICES=0`
On the Windows platform, DataLoader only supports single-process mode, so you need to set `num_workers` to 0;
- macOS
GPU mode is not supported, you need to set `use_gpu` to False in the configuration file, and the rest of the training evaluation prediction commands are exactly the same as Linux GPU.
- Linux DCU
Running on a DCU device requires setting the environment variable `export HIP_VISIBLE_DEVICES=0,1,2,3`, and the rest of the training and evaluation prediction commands are exactly the same as the Linux GPU.
> 1. Compared with the model v2.0, the 2.1 version of the detection model has a improvement in accuracy, and the 2.1 version of the recognition model has optimizations in accuracy and speed with CPU.
> 1. Compared with the model v2, the 3rd version of the detection model has a improvement in accuracy, and the 2.1 version of the recognition model has optimizations in accuracy and speed with CPU.
> 2. Compared with [models 1.1](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md), which are trained with static graph programming paradigm, models 2.0 are the dynamic graph trained version and achieve close performance.
> 2. Compared with [models 1.1](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md), which are trained with static graph programming paradigm, models 2.0 or higher are the dynamic graph trained version and achieve close performance.
> 3. All models in this tutorial are all ppocr-series models, for more introduction of algorithms and models based on public dataset, you can refer to [algorithm overview tutorial](./algorithm_overview_en.md).
> 3. All models in this tutorial are all ppocr-series models, for more introduction of algorithms and models based on public dataset, you can refer to [algorithm overview tutorial](./algorithm_overview_en.md).
-[OCR Model List（V2.1, updated on 2021.9.6）](#ocr-model-listv21-updated-on-202196)
-[OCR Model List（V3, updated on 2022.4.28）]()
-[1. Text Detection Model](#1-text-detection-model)
-[1. Text Detection Model](#1-text-detection-model)
-[1.1 Chinese Detection Model](#1.1)
-[2.2 English Detection Model](#1.2)
-[1.3 Multilingual Detection Model](#1.3)
-[2. Text Recognition Model](#2-text-recognition-model)
-[2. Text Recognition Model](#2-text-recognition-model)
-[2.1 Chinese Recognition Model](#21-chinese-recognition-model)
-[2.1 Chinese Recognition Model](#21-chinese-recognition-model)
-[2.2 English Recognition Model](#22-english-recognition-model)
-[2.2 English Recognition Model](#22-english-recognition-model)
...
@@ -28,14 +31,42 @@ Relationship of the above models is as follows.
...
@@ -28,14 +31,42 @@ Relationship of the above models is as follows.
|ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
|ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
|ch_PP-OCRv2_rec_slim|[New] Slim qunatization with distillation lightweight model, supporting Chinese, English, multilingual text recognition|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) |
|ch_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition |[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 4.9M |[inference model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/ch/ch_PP-OCRv3_rec_slim_train.tar) / [lite model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.nb) |
|ch_PP-OCRv2_rec|[New] Original lightweight model, supporting Chinese, English, multilingual text recognition|[ch_PP-OCRv2_rec_distillation.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) |
|ch_PP-OCRv3_rec| [New] Original lightweight model, supporting Chinese, English, multilingual text recognition |[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 12.4M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
|ch_PP-OCRv2_rec_slim| Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) |
|ch_PP-OCRv2_rec| Original lightweight model, supporting Chinese, English, multilingual text recognition |[ch_PP-OCRv2_rec_distillation.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) |
|ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) |
|ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) |
|ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
|ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
|ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |
|ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |
...
@@ -58,6 +91,8 @@ Relationship of the above models is as follows.
...
@@ -58,6 +91,8 @@ Relationship of the above models is as follows.
|en_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting english, English text recognition |[en_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec_distillation.yml)| 4.9M |[inference model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_train.tar) / [lite model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.nb) |
|en_PP-OCRv3_rec| [New] Original lightweight model, supporting english, English, multilingual text recognition |[en_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec_distillation.yml)| 12.4M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
|en_number_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| 2.7M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_train.tar) |
|en_number_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| 2.7M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_train.tar) |
|en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) |
|en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) |
| Chinese and English ultra-lightweight PP-OCRv3 model（16.2M） | ch_PP-OCRv3_xx | Mobile & Server | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
| English ultra-lightweight PP-OCRv3 model（13.4M） | en_PP-OCRv3_xx | Mobile & Server | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/ch_ppocr_mobile_v2.0_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） | ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） | ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)|
| Chinese and English ultra-lightweight PP-OCR model (9.4M) | ch_ppocr_mobile_v2.0_xx | Mobile & server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) |
| Chinese and English ultra-lightweight PP-OCR model (9.4M) | ch_ppocr_mobile_v2.0_xx | Mobile & server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) |
| Chinese and English general PP-OCR model (143.4M) | ch_ppocr_server_v2.0_xx | Server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) |
| Chinese and English general PP-OCR model (143.4M) | ch_ppocr_server_v2.0_xx | Server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) |
*[2.8 Training on other platform(Windows/macOS/Linux DCU)](#28)
-[5. Convert to Inference Model](#Inference)
-[3. Evaluation and Test](#3-evaluation-and-test)
*[3.1 Evaluation](#31-evaluation)
*[3.2 Test](#32-test)
-[4. Inference](#4-inference)
-[5. FAQ](#5-faq)
<aname="DATA_PREPARATION"></a>
<aname="DATA_PREPARATION"></a>
## 1. Data Preparation
## 1. Data Preparation
### 1.1 DataSet Preparation
PaddleOCR supports two data formats:
To prepare datasets, refer to [ocr_datasets](./dataset/ocr_datasets.md) .
-`LMDB` is used to train data sets stored in lmdb format（LMDBDataSet）;
-`general data` is used to train data sets stored in text files（SimpleDataSet）:
Please organize the dataset as follows:
The default storage path for training data is `PaddleOCR/train_data`, if you already have a dataset on your disk, just create a soft link to the dataset directory:
If you want to use your own data for training, please refer to the following to organize your data.
- Training set
It is recommended to put the training images in the same folder, and use a txt file (rec_gt_train.txt) to store the image path and label. The contents of the txt file are as follows:
* Note: by default, the image path and image label are split with \t, if you use other methods to split, it will cause training error
```
" Image file name Image annotation "
train_data/rec/train/word_001.jpg 简单可依赖
train_data/rec/train/word_002.jpg 用科技让复杂的世界更简单
...
```
The final training set should have the following file structure:
```
|-train_data
|-rec
|- rec_gt_train.txt
|- train
|- word_001.png
|- word_002.jpg
|- word_003.jpg
| ...
```
- Test set
Similar to the training set, the test set also needs to be provided a folder containing all images (test) and a rec_gt_test.txt. The structure of the test set is as follows:
```
|-train_data
|-rec
|-ic15_data
|- rec_gt_test.txt
|- test
|- word_001.jpg
|- word_002.jpg
|- word_003.jpg
| ...
```
<aname="Dataset_download"></a>
### 1.2 Dataset Download
- ICDAR2015
If you do not have a dataset locally, you can download it on the official website [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads).
Also refer to [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ，download the lmdb format dataset required for benchmark
PaddleOCR provides label files for training the icdar2015 dataset, which can be downloaded in the following ways:
PaddleOCR provides label files for training the icdar2015 dataset, which can be downloaded in the following ways:
...
@@ -122,7 +58,7 @@ The multi-language model training method is the same as the Chinese model. The t
...
@@ -122,7 +58,7 @@ The multi-language model training method is the same as the Chinese model. The t
<aname="Dictionary"></a>
<aname="Dictionary"></a>
### 1.3 Dictionary
### 1.2 Dictionary
Finally, a dictionary ({word_dict_name}.txt) needs to be provided so that when the model is trained, all the characters that appear can be mapped to the dictionary index.
Finally, a dictionary ({word_dict_name}.txt) needs to be provided so that when the model is trained, all the characters that appear can be mapped to the dictionary index.
...
@@ -171,11 +107,8 @@ If you need to customize dic file, please add character_dict_path field in confi
...
@@ -171,11 +107,8 @@ If you need to customize dic file, please add character_dict_path field in confi
If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `True`.
If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `True`.
<aname="TRAINING"></a>
## 2.Training
<aname="Data_Augmentation"></a>
<aname="Data_Augmentation"></a>
### 2.1 Data Augmentation
### 1.5 Data Augmentation
PaddleOCR provides a variety of data augmentation methods. All the augmentation methods are enabled by default.
PaddleOCR provides a variety of data augmentation methods. All the augmentation methods are enabled by default.
Each disturbance method is selected with a 40% probability during the training process. For specific code implementation, please refer to: [rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
Each disturbance method is selected with a 40% probability during the training process. For specific code implementation, please refer to: [rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
<aname="Training"></a>
<aname="TRAINING"></a>
### 2.2 General Training
## 2.Training
PaddleOCR provides training scripts, evaluation scripts, and prediction scripts. In this section, the CRNN recognition model will be used as an example:
PaddleOCR provides training scripts, evaluation scripts, and prediction scripts. In this section, the CRNN recognition model will be used as an example:
<aname="21-start-training"></a>
### 2.1 Start Training
First download the pretrain model, you can download the trained model to finetune on the icdar2015 data:
First download the pretrain model, you can download the trained model to finetune on the icdar2015 data:
```
```
...
@@ -286,8 +222,99 @@ Eval:
...
@@ -286,8 +222,99 @@ Eval:
```
```
**Note that the configuration file for prediction/evaluation must be consistent with the training.**
**Note that the configuration file for prediction/evaluation must be consistent with the training.**
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.
**Note**: The priority of `Global.checkpoints` is higher than that of `Global.pretrained_model`, that is, when two parameters are specified at the same time, the model specified by `Global.checkpoints` will be loaded first. If the model path specified by `Global.checkpoints` is wrong, the one specified by `Global.pretrained_model` will be loaded.
<aname="23-training-with-new-backbone"></a>
### 2.3 Training with New Backbone
The network part completes the construction of the network, and PaddleOCR divides the network into four parts, which are under [ppocr/modeling](../../ppocr/modeling). The data entering the network will pass through these four parts in sequence(transforms->backbones->
necks->heads).
```bash
├── architectures # Code for building network
├── transforms # Image Transformation Module
├── backbones # Feature extraction module
├── necks # Feature enhancement module
└── heads # Output module
```
If the Backbone to be replaced has a corresponding implementation in PaddleOCR, you can directly modify the parameters in the `Backbone` part of the configuration yml file.
However, if you want to use a new Backbone, an example of replacing the backbones is as follows:
1. Create a new file under the [ppocr/modeling/backbones](../../ppocr/modeling/backbones) folder, such as my_backbone.py.
2. Add code in the my_backbone.py file, the sample code is as follows:
```python
importpaddle
importpaddle.nnasnn
importpaddle.nn.functionalasF
classMyBackbone(nn.Layer):
def__init__(self,*args,**kwargs):
super(MyBackbone,self).__init__()
# your init code
self.conv=nn.xxxx
defforward(self,inputs):
# your network forward
y=self.conv(inputs)
returny
```
3. Import the added module in the [ppocr/modeling/backbones/\__init\__.py](../../ppocr/modeling/backbones/__init__.py) file.
After adding the four-part modules of the network, you only need to configure them in the configuration file to use, such as:
```yaml
Backbone:
name:MyBackbone
args1:args1
```
**NOTE**: More details about replace Backbone and other mudule can be found in [doc](add_new_algorithm_en.md).
<aname="24-amp-training"></a>
### 2.4 Mixed Precision Training
If you want to speed up your training further, you can use [Auto Mixed Precision Training](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/01_paddle2.0_introduction/basic_concept/amp_cn.html), taking a single machine and a single gpu as an example, the commands are as follows:
During multi-machine multi-gpu training, use the `--ips` parameter to set the used machine IP address, and the `--gpus` parameter to set the used GPU ID:
**Note:** When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. In addition, training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`.
<a name="kd"></a>
### 2.6 Training with Knowledge Distillation
Knowledge distillation is supported in PaddleOCR for text recognition training process. For more details, please refer to [doc](./knowledge_distillation_en.md).
<a name="Multi_language"></a>
<a name="Multi_language"></a>
### 2.3 Multi-language Training
### 2.7 Multi-language Training
Currently, the multi-language algorithms supported by PaddleOCR are:
Currently, the multi-language algorithms supported by PaddleOCR are:
...
@@ -343,25 +370,36 @@ Eval:
...
@@ -343,25 +370,36 @@ Eval:
...
...
```
```
<aname="kd"></a>
<a name="28"></a>
### 2.8 Training on other platform(Windows/macOS/Linux DCU)
### 2.4 Training with Knowledge Distillation
- Windows GPU/CPU
The Windows platform is slightly different from the Linux platform:
Windows platform only supports `single gpu` training and inference, specify GPU for training `set CUDA_VISIBLE_DEVICES=0`
On the Windows platform, DataLoader only supports single-process mode, so you need to set `num_workers` to 0;
Knowledge distillation is supported in PaddleOCR for text recognition training process. For more details, please refer to [doc](./knowledge_distillation_en.md).
- macOS
GPU mode is not supported, you need to set `use_gpu` to False in the configuration file, and the rest of the training evaluation prediction commands are exactly the same as Linux GPU.
- Linux DCU
Running on a DCU device requires setting the environment variable `export HIP_VISIBLE_DEVICES=0,1,2,3`, and the rest of the training and evaluation prediction commands are exactly the same as the Linux GPU.
<aname="EVALUATION"></a>
<a name="3-evaluation-and-test"></a>
## 3. Evaluation and Test
## 3. Evalution
<a name="31-evaluation"></a>
### 3.1 Evaluation
The model parameters during training are saved in the `Global.save_model_dir` directory by default. When evaluating indicators, you need to set `Global.checkpoints` to point to the saved parameter file. The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml` file.
The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml` file.
```
```
# GPU evaluation, Global.checkpoints is the weight to be tested
# GPU evaluation, Global.checkpoints is the weight to be tested
The inference model (the model saved by `paddle.jit.save`) is generally a solidified model saved after the model training is completed, and is mostly used to give prediction in deployment.
## 5. Convert to Inference Model
The model saved during the training process is the checkpoints model, which saves the parameters of the model and is mostly used to resume training.
Compared with the checkpoints model, the inference model will additionally save the structural information of the model. Therefore, it is easier to deploy because the model structure and model parameters are already solidified in the inference model file, and is suitable for integration with actual systems.
The recognition model is converted to the inference model in the same way as the detection, as follows:
The recognition model is converted to the inference model in the same way as the detection, as follows:
...
@@ -443,6 +486,7 @@ If you have a model trained on your own dataset with a different dictionary file
...
@@ -443,6 +486,7 @@ If you have a model trained on your own dataset with a different dictionary file
After the conversion is successful, there are three files in the model save directory:
After the conversion is successful, there are three files in the model save directory:
```
```
inference/en_PP-OCRv3_rec/
inference/en_PP-OCRv3_rec/
├── inference.pdiparams # The parameter file of recognition inference model
├── inference.pdiparams # The parameter file of recognition inference model
├── inference.pdiparams.info # The parameter information of recognition inference model, which can be ignored
├── inference.pdiparams.info # The parameter information of recognition inference model, which can be ignored
Q1: After the training model is transferred to the inference model, the prediction effect is inconsistent?
**A**: There are many such problems, and the problems are mostly caused by inconsistent preprocessing and postprocessing parameters when the trained model predicts and the preprocessing and postprocessing parameters when the inference model predicts. You can compare whether there are differences in preprocessing, postprocessing, and prediction in the configuration files used for training.
@@ -94,7 +94,7 @@ The current open source models, data sets and magnitudes are as follows:
...
@@ -94,7 +94,7 @@ The current open source models, data sets and magnitudes are as follows:
- Chinese data set, LSVT street view data set crops the image according to the truth value, and performs position calibration, a total of 30w images. In addition, based on the LSVT corpus, 500w of synthesized data.
- Chinese data set, LSVT street view data set crops the image according to the truth value, and performs position calibration, a total of 30w images. In addition, based on the LSVT corpus, 500w of synthesized data.
- Small language data set, using different corpora and fonts, respectively generated 100w synthetic data set, and using ICDAR-MLT as the verification set.
- Small language data set, using different corpora and fonts, respectively generated 100w synthetic data set, and using ICDAR-MLT as the verification set.
Among them, the public data sets are all open source, users can search and download by themselves, or refer to [Chinese data set](./datasets_en.md), synthetic data is not open source, users can use open source synthesis tools to synthesize by themselves. Synthesis tools include [text_renderer](https://github.com/Sanster/text_renderer), [SynthText](https://github.com/ankush-me/SynthText), [TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator) etc.
Among them, the public data sets are all open source, users can search and download by themselves, or refer to [Chinese data set](dataset/datasets_en.md), synthetic data is not open source, users can use open source synthesis tools to synthesize by themselves. Synthesis tools include [text_renderer](https://github.com/Sanster/text_renderer), [SynthText](https://github.com/ankush-me/SynthText), [TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator) etc.
