From 25ffa816f715a88b3ba66033a48be78ed0b24538 Mon Sep 17 00:00:00 2001 From: Weihang Wang <79965746+wkml@users.noreply.github.com> Date: Wed, 27 Dec 2023 19:41:17 +0800 Subject: [PATCH] doc: add doc for satrn (#11397) --- doc/doc_ch/algorithm_overview.md | 3 +- doc/doc_ch/algorithm_rec-satrn.md | 112 +++++++++++++++++++++++++++ doc/doc_en/algorithm_overview_en.md | 2 + doc/doc_en/algorithm_rec_satrn_en.md | 111 ++++++++++++++++++++++++++ 4 files changed, 227 insertions(+), 1 deletion(-) create mode 100644 doc/doc_ch/algorithm_rec-satrn.md create mode 100644 doc/doc_en/algorithm_rec_satrn_en.md diff --git a/doc/doc_ch/algorithm_overview.md b/doc/doc_ch/algorithm_overview.md index d8fbeb607..b8d4aedc1 100755 --- a/doc/doc_ch/algorithm_overview.md +++ b/doc/doc_ch/algorithm_overview.md @@ -88,6 +88,7 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广 - [x] [RFL](./algorithm_rec_rfl.md) - [x] [ParseQ](./algorithm_rec_parseq.md) - [x] [CPPD](./algorithm_rec_cppd.md) +- [x] [SATRN](./algorithm_rec_satrn.md) 参考[DTRB](https://arxiv.org/abs/1904.01906)[3]文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下： @@ -114,7 +115,7 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广 |RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl_att_train.tar) | |ParseQ|VIT| 91.24% | rec_vit_parseq_synth | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/parseq/rec_vit_parseq_synth.tgz) | |CPPD|SVTR-Base| 93.8% | rec_svtrnet_cppd_base_en | [训练模型](https://paddleocr.bj.bcebos.com/CCPD/rec_svtr_cppd_base_en_train.tar) | - +|SATRN|ShallowCNN| 88.05% | rec_satrn | [训练模型](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a) | diff --git a/doc/doc_ch/algorithm_rec-satrn.md b/doc/doc_ch/algorithm_rec-satrn.md new file mode 100644 index 000000000..ec55af03d --- /dev/null +++ b/doc/doc_ch/algorithm_rec-satrn.md @@ -0,0 +1,112 @@ +# SATRN + +- [1. 算法简介](#1) +- [2. 环境配置](#2) +- [3. 模型训练、评估、预测](#3) + - [3.1 训练](#3-1) + - [3.2 评估](#3-2) + - [3.3 预测](#3-3) +- [4. 推理部署](#4) + - [4.1 Python推理](#4-1) + - [4.2 C++推理](#4-2) + - [4.3 Serving服务化部署](#4-3) + - [4.4 更多推理部署](#4-4) +- [5. FAQ](#5) + + +## 1. 算法简介 + +论文信息： +> [On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention](https://arxiv.org/abs/1910.04396) +> Junyeop Lee, Sungrae Park, Jeonghun Baek, Seong Joon Oh, Seonghyeon Kim, Hwalsuk Lee +> CVPR, 2020 +参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下： + +|模型|骨干网络|Avg Accuracy|配置文件|下载链接| +|---|---|---|---|---| +|SATRN|ShallowCNN|88.05%|[configs/rec/rec_satrn.yml](../../configs/rec/rec_satrn.yml)|[训练模型](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a)| + + + + +## 2. 环境配置 +请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](./clone.md)克隆项目代码。 + + + +## 3. 模型训练、评估、预测 + +请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练不同的识别模型只需要**更换配置文件**即可。 + +- 训练 + +在完成数据准备后，便可以启动训练，训练命令如下： + +``` +#单卡训练（训练周期长，不建议） +python3 tools/train.py -c configs/rec/rec_satrn.yml +#多卡训练，通过--gpus参数指定卡号 +python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c rec_satrn.yml +``` + +- 评估 + +``` +# GPU 评估， Global.pretrained_model 为待测权重 +python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model={path/to/weights}/best_accuracy +``` + +- 预测： + +``` +# 预测使用的配置文件必须与训练一致 +python3 tools/infer_rec.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png +``` + + +## 4. 推理部署 + + +### 4.1 Python推理 +首先将SATRN文本识别训练过程中保存的模型，转换成inference model。（ [模型下载地址](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a) )，可以使用如下命令进行转换： + +``` +python3 tools/export_model.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model=./rec_satrn/best_accuracy Global.save_inference_dir=./inference/rec_satrn +``` + +SATRN文本识别模型推理，可以执行如下命令： + +``` +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_satrn/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SATRN" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False +``` + + +### 4.2 C++推理 + +由于C++预处理后处理还未支持SATRN，所以暂未支持 + + +### 4.3 Serving服务化部署 + +暂不支持 + + +### 4.4 更多推理部署 + +暂不支持 + + +## 5. FAQ + +## 引用 + +```bibtex +@article{lee2019recognizing, + title={On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention}, + author={Junyeop Lee and Sungrae Park and Jeonghun Baek and Seong Joon Oh and Seonghyeon Kim and Hwalsuk Lee}, + year={2019}, + eprint={1910.04396}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} +``` \ No newline at end of file diff --git a/doc/doc_en/algorithm_overview_en.md b/doc/doc_en/algorithm_overview_en.md index ee4051426..92b1e4f71 100755 --- a/doc/doc_en/algorithm_overview_en.md +++ b/doc/doc_en/algorithm_overview_en.md @@ -85,6 +85,7 @@ Supported text recognition algorithms (Click the link to get the tutorial): - [x] [RFL](./algorithm_rec_rfl_en.md) - [x] [ParseQ](./algorithm_rec_parseq.md) - [x] [CPPD](./algorithm_rec_cppd_en.md) +- [x] [SATRN](./algorithm_rec_satrn_en.md) Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow: @@ -111,6 +112,7 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r |RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl_att_train.tar) | |ParseQ|VIT| 91.24% | rec_vit_parseq_synth | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/parseq/rec_vit_parseq_synth.tgz) | |CPPD|SVTR-Base| 93.8% | rec_svtrnet_cppd_base_en | [trained model](https://paddleocr.bj.bcebos.com/CCPD/rec_svtr_cppd_base_en_train.tar) | +|SATRN|ShallowCNN| 88.05% | rec_satrn | [trained model](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a) | diff --git a/doc/doc_en/algorithm_rec_satrn_en.md b/doc/doc_en/algorithm_rec_satrn_en.md new file mode 100644 index 000000000..b36960863 --- /dev/null +++ b/doc/doc_en/algorithm_rec_satrn_en.md @@ -0,0 +1,111 @@ +# SATRN + +- [1. Introduction](#1) +- [2. Environment](#2) +- [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) + + +## 1. Introduction + +论文信息： +> [On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention](https://arxiv.org/abs/1910.04396) +> Junyeop Lee, Sungrae Park, Jeonghun Baek, Seong Joon Oh, Seonghyeon Kim, Hwalsuk Lee +> 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: + +|Model|Backbone|config|Acc|Download link| +| --- | --- | --- | --- | --- | +|SATRN|ShallowCNN|88.05%|[configs/rec/rec_satrn.yml](../../configs/rec/rec_satrn.yml)|[训练模型](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a)| + + + +## 2. Environment +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. + + + +## 3. Model Training / Evaluation / Prediction + +Please refer to [Text Recognition Tutorial](./recognition_en.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) +python3 tools/train.py -c configs/rec/rec_satrn.yml +#Multi GPU training, specify the gpu number through the --gpus parameter +python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/rec/rec_satrn.yml +``` + +Evaluation: + +``` +# GPU evaluation +python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model={path/to/weights}/best_accuracy +``` + +Prediction: + +``` +# The configuration file used for prediction must match the training +python3 tools/infer_rec.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png +``` + + +## 4. Inference and Deployment + + +### 4.1 Python Inference +First, the model saved during the SATRN text recognition training process is converted into an inference model. ( [Model download link](https://pan.baidu.com/s/10J-Bsd881bimKaclKszlaQ?pwd=lk8a) ), you can use the following command to convert: + +``` +python3 tools/export_model.py -c configs/rec/rec_satrn.yml -o Global.pretrained_model=./rec_satrn_train/best_accuracy Global.save_inference_dir=./inference/rec_satrn +``` + +For SATRN text recognition model inference, the following commands can be executed: + +``` +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_satrn/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SATRN" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False +``` + + +### 4.2 C++ Inference + +Not supported + + +### 4.3 Serving + +Not supported + + +### 4.4 More + +Not supported + + +## 5. FAQ + +## 引用 + +```bibtex +@article{lee2019recognizing, + title={On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention}, + author={Junyeop Lee and Sungrae Park and Jeonghun Baek and Seong Joon Oh and Seonghyeon Kim and Hwalsuk Lee}, + year={2019}, + eprint={1910.04396}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} +``` \ No newline at end of file