diff --git a/PPOCRLabel/README.md b/PPOCRLabel/README.md index f72ae96679d9ca3ba1585c49ce8762cd73e97d24..7276213f14983ea8b401e6ccf64d93d0f6d6ba13 100644 --- a/PPOCRLabel/README.md +++ b/PPOCRLabel/README.md @@ -120,6 +120,11 @@ For some data that are difficult to recognize, the recognition results will not ``` pyrcc5 -o libs/resources.py resources.qrc ``` +- If you get an error ``` module 'cv2' has no attribute 'INTER_NEAREST'```, you need to delete all opencv related packages first, and then reinstall the headless version of opencv + ``` + pip install opencv-contrib-python-headless + ``` + ### Related 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg) diff --git a/PPOCRLabel/README_ch.md b/PPOCRLabel/README_ch.md index 334cb2860848dd7def22c537b0e10cd5a9435289..01513ba7070bea5af88f1148c3f7d8e52ce2a349 100644 --- a/PPOCRLabel/README_ch.md +++ b/PPOCRLabel/README_ch.md @@ -88,15 +88,23 @@ python3 PPOCRLabel.py --lang ch ### 错误提示 - 如果同时使用whl包安装了paddleocr，其优先级大于通过paddleocr.py调用PaddleOCR类，whl包未更新时会导致程序异常。 + - PPOCRLabel**不支持对中文文件名**的图片进行自动标注。 + - 针对Linux用户：：如果您在打开软件过程中出现**objc[XXXXX]**开头的错误，证明您的opencv版本太高，建议安装4.2版本： ``` pip install opencv-python==4.2.0.32 ``` -- 如果出现''Missing string id '开头的错误，需要重新编译资源： + +- 如果出现 ```Missing string id``` 开头的错误，需要重新编译资源： ``` pyrcc5 -o libs/resources.py resources.qrc ``` + +- 如果出现``` module 'cv2' has no attribute 'INTER_NEAREST'```错误，需要首先删除所有opencv相关包，然后重新安装headless版本的opencv + ``` + pip install opencv-contrib-python-headless + ``` ### 参考资料 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg) diff --git a/README_ch.md b/README_ch.md old mode 100644 new mode 100755 index d4383eb4989d746ba4fbf124324f45abfb06302a..afdd053613866c3b683881ca50119fa231a4ec85 --- a/README_ch.md +++ b/README_ch.md @@ -9,7 +9,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式 **近期更新** - 2020.12.15 更新数据合成工具[Style-Text](./StyleText/README_ch.md)，可以批量合成大量与目标场景类似的图像，在多个场景验证，效果明显提升。 -- 2020.12.07 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题，总数124个，并且计划以后每周一都会更新，欢迎大家持续关注。 +- 2020.12.14 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题，总数127个，每周一都会更新，欢迎大家持续关注。 - 2020.11.25 更新半自动标注工具[PPOCRLabel](./PPOCRLabel/README_ch.md)，辅助开发者高效完成标注任务，输出格式与PP-OCR训练任务完美衔接。 - 2020.9.22 更新PP-OCR技术文章，https://arxiv.org/abs/2009.09941 - [More](./doc/doc_ch/update.md) @@ -39,6 +39,14 @@ PaddleOCR同时支持动态图与静态图两种编程范式 上图是通用ppocr_server模型效果展示，更多效果图请见[效果展示页面](./doc/doc_ch/visualization.md)。 + +## 欢迎加入PaddleOCR技术交流群 +- 微信扫描二维码加入官方交流群，获得更高效的问题答疑，与各行各业开发者充分交流，期待您的加入。 + +
+ +
+ ## 快速体验 - PC端：超轻量级中文OCR在线体验地址：https://www.paddlepaddle.org.cn/hub/scene/ocr @@ -121,7 +129,7 @@ PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测、检测框 - 英文模型
- +
- 其他语言模型 @@ -130,13 +138,6 @@ PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测、检测框 - -## 欢迎加入PaddleOCR技术交流群 -请扫描下面二维码，完成问卷填写，获取加群二维码和OCR方向的炼丹秘籍 - -
- -
## 许可证书 diff --git a/configs/det/det_mv3_db.yml b/configs/det/det_mv3_db.yml index 36a6f755383e525a8a496b060465cf027f3f31f8..5c8a0923427bc96c10f0a1275c3639cea735f1f4 100644 --- a/configs/det/det_mv3_db.yml +++ b/configs/det/det_mv3_db.yml @@ -2,11 +2,11 @@ Global: use_gpu: true epoch_num: 1200 log_smooth_window: 20 - print_batch_step: 2 + print_batch_step: 10 save_model_dir: ./output/db_mv3/ save_epoch_step: 1200 - # evaluation is run every 5000 iterations after the 4000th iteration - eval_batch_step: [4000, 5000] + # evaluation is run every 2000 iterations + eval_batch_step: [0, 2000] # if pretrained_model is saved in static mode, load_static_weights must set to True load_static_weights: True cal_metric_during_train: False @@ -39,7 +39,7 @@ Loss: alpha: 5 beta: 10 ohem_ratio: 3 - + Optimizer: name: Adam beta1: 0.9 @@ -100,7 +100,7 @@ Train: loader: shuffle: True drop_last: False - batch_size_per_card: 4 + batch_size_per_card: 16 num_workers: 8 Eval: @@ -128,4 +128,4 @@ Eval: shuffle: False drop_last: False batch_size_per_card: 1 # must be 1 - num_workers: 2 \ No newline at end of file + num_workers: 8 \ No newline at end of file diff --git a/configs/det/det_r50_vd_db.yml b/configs/det/det_r50_vd_db.yml index b70ab7505a4c1970f084b6c02233526d7f7188b9..f1188fe357ea5c02f8839239e788a629221bf118 100644 --- a/configs/det/det_r50_vd_db.yml +++ b/configs/det/det_r50_vd_db.yml @@ -5,8 +5,8 @@ Global: print_batch_step: 10 save_model_dir: ./output/det_r50_vd/ save_epoch_step: 1200 - # evaluation is run every 5000 iterations after the 4000th iteration - eval_batch_step: [5000,4000] + # evaluation is run every 2000 iterations + eval_batch_step: [0,2000] # if pretrained_model is saved in static mode, load_static_weights must set to True load_static_weights: True cal_metric_during_train: False diff --git a/configs/det/det_r50_vd_sast_totaltext.yml b/configs/det/det_r50_vd_sast_totaltext.yml index 257ecf2490bdde6280cf4b20bb66f2457b4b833b..a92f1b6e539b9f78d2edc705cd9cda0fb6522c28 100755 --- a/configs/det/det_r50_vd_sast_totaltext.yml +++ b/configs/det/det_r50_vd_sast_totaltext.yml @@ -60,7 +60,8 @@ Metric: Train: dataset: name: SimpleDataSet - label_file_path: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt] + data_dir: ./train_data/ + label_file_list: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt] data_ratio_list: [0.5, 0.5] transforms: - DecodeImage: # load image diff --git a/deploy/cpp_infer/readme.md b/deploy/cpp_infer/readme.md index 7296936643af87817da40592753550fed9a7c8b5..66302a0114186306fde0572fca23aabd27620f95 100644 --- a/deploy/cpp_infer/readme.md +++ b/deploy/cpp_infer/readme.md @@ -103,17 +103,17 @@ make inference_lib_dist 更多编译参数选项可以参考Paddle C++预测库官网：[https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html)。 -* 编译完成之后，可以在`build/fluid_inference_install_dir/`文件下看到生成了以下文件及文件夹。 +* 编译完成之后，可以在`build/paddle_inference_install_dir/`文件下看到生成了以下文件及文件夹。 ``` -build/fluid_inference_install_dir/ +build/paddle_inference_install_dir/ |-- CMakeCache.txt |-- paddle |-- third_party |-- version.txt ``` -其中`paddle`就是之后进行C++预测时所需的Paddle库，`version.txt`中包含当前预测库的版本信息。 +其中`paddle`就是C++预测所需的Paddle库，`version.txt`中包含当前预测库的版本信息。 #### 1.2.2 直接下载安装 diff --git a/deploy/cpp_infer/tools/config.txt b/deploy/cpp_infer/tools/config.txt index 40beea3a2e6f0260a42202d6411ffb10907bf871..95d7989bfc06a9e061874a824d070ca60bc3848d 100644 --- a/deploy/cpp_infer/tools/config.txt +++ b/deploy/cpp_infer/tools/config.txt @@ -11,10 +11,15 @@ max_side_len 960 det_db_thresh 0.3 det_db_box_thresh 0.5 det_db_unclip_ratio 2.0 -det_model_dir ./inference/det_db +det_model_dir ./inference/ch__ppocr_mobile_v2.0_det_infer/ + +# cls config +use_angle_cls 0 +cls_model_dir ./inference/ch_ppocr_mobile_v2.0_cls_infer/ +cls_thresh 0.9 # rec config -rec_model_dir ./inference/rec_crnn +rec_model_dir ./inference/ch_ppocr_mobile_v2.0_rec_infer/ char_list_file ../../ppocr/utils/ppocr_keys_v1.txt # show the detection results diff --git a/doc/doc_ch/FAQ.md b/doc/doc_ch/FAQ.md old mode 100644 new mode 100755 index 57fd8c2e6fb0908671eeca1d4d438121979a02f8..27b3126cd45d2fc7043d6b55f9192984cb08e3ec --- a/doc/doc_ch/FAQ.md +++ b/doc/doc_ch/FAQ.md @@ -9,44 +9,42 @@ ## PaddleOCR常见问题汇总(持续更新) -* [近期更新（2020.12.07）](#近期更新) +* [近期更新（2020.12.14）](#近期更新) * [【精选】OCR精选10个问题](#OCR精选10个问题) * [【理论篇】OCR通用30个问题](#OCR通用问题) * [基础知识7题](#基础知识) * [数据集7题](#数据集2) * [模型训练调优7题](#模型训练调优2) * [预测部署9题](#预测部署2) -* [【实战篇】PaddleOCR实战84个问题](#PaddleOCR实战问题) - * [使用咨询20题](#使用咨询) +* [【实战篇】PaddleOCR实战87个问题](#PaddleOCR实战问题) + * [使用咨询21题](#使用咨询) * [数据集17题](#数据集3) - * [模型训练调优24题](#模型训练调优3) - * [预测部署23题](#预测部署3) + * [模型训练调优25题](#模型训练调优3) + * [预测部署24题](#预测部署3) -## 近期更新（2020.12.07） +## 近期更新（2020.12.14） -#### Q2.4.9：弯曲文本有试过opencv的TPS进行弯曲校正吗？ +#### Q3.1.21：PaddleOCR支持动态图吗？ -**A**：opencv的tps需要标出上下边界对应的点，这些点很难通过传统方法或者深度学习方法获取。PaddleOCR里StarNet网络中的tps模块实现了自动学点，自动校正，可以直接尝试这个。 +**A**：动态图版本正在紧锣密鼓开发中，将于2020年12月16日发布，敬请关注。 -#### Q3.3.20: 文字检测时怎么模糊的数据增强？ +#### Q3.3.23：检测模型训练或预测时出现elementwise_add报错 -**A**: 模糊的数据增强需要修改代码进行添加，以DB为例，参考[Normalize](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/ppocr/data/imaug/operators.py#L60) ,添加模糊的增强就行 +**A**：设置的输入尺寸必须是32的倍数，否则在网络多次下采样和上采样后，feature map会产生1个像素的diff，从而导致elementwise_add时报shape不匹配的错误。 -#### Q3.3.21: 文字检测时怎么更改图片旋转的角度，实现360度任意旋转？ +#### Q3.3.24: DB检测训练输入尺寸640，可以改大一些吗？ -**A**: 将[这里](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/ppocr/data/imaug/iaa_augment.py#L64) 的(-10,10) 改为(-180,180)即可 +**A**: 不建议改大。检测模型训练输入尺寸是预处理中random crop后的尺寸，并非直接将原图进行resize，多数场景下这个尺寸并不小了，改大后可能反而并不合适，而且训练会变慢。另外，代码里可能有的地方参数按照预设输入尺寸适配的，改大后可能有隐藏风险。 -#### Q3.3.22: 训练数据的长宽比过大怎么修改shape +#### Q3.3.25: 识别模型训练时，loss能正常下降，但acc一直为0 -**A**: 识别修改[这里](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yaml#L75) , -检测修改[这里](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml#L85) +**A**: 识别模型训练初期acc为0是正常的，多训一段时间指标就上来了。 +#### Q3.4.24：DB模型能正确推理预测，但换成EAST或SAST模型时报错或结果不正确 -#### Q3.4.23：安装paddleocr后，提示没有paddle - -**A**：这是因为paddlepaddle gpu版本和cpu版本的名称不一致，现在已经在[whl的文档](./whl.md)里做了安装说明。 +**A**：使用EAST或SAST模型进行推理预测时，需要在命令中指定参数--det_algorithm="EAST" 或 --det_algorithm="SAST"，使用DB时不用指定是因为该参数默认值是"DB"：https://github.com/PaddlePaddle/PaddleOCR/blob/e7a708e9fdaf413ed7a14da8e4a7b4ac0b211e42/tools/infer/utility.py#L43 ## 【精选】OCR精选10个问题 @@ -373,15 +371,15 @@ |8.6M超轻量中文OCR模型|MobileNetV3+MobileNetV3|det_mv3_db.yml|rec_chinese_lite_train.yml| |通用中文OCR模型|Resnet50_vd+Resnet34_vd|det_r50_vd_db.yml|rec_chinese_common_train.yml| -#### ！！Q3.1.18：如何加入自己的检测算法？ +#### Q3.1.18：如何加入自己的检测算法？ **A**：1. 在ppocr/modeling对应目录下分别选择backbone，head。如果没有可用的可以新建文件并添加 2. 在ppocr/data下选择对应的数据处理处理方式，如果没有可用的可以新建文件并添加 - 3. 在ppocr/losses下新建文件并编写loss - 4. 在ppocr/postprocess下新建文件并编写后处理算法 - 5. 将上面四个步骤里新添加的类或函数参照yml文件写到配置中 + 3. 在ppocr/losses下新建文件并编写loss + 4. 在ppocr/postprocess下新建文件并编写后处理算法 + 5. 将上面四个步骤里新添加的类或函数参照yml文件写到配置中 -#### ！！Q3.1.19：训练的时候报错`reader raised an exception`，但是具体不知道是啥问题？ +#### Q3.1.19：训练的时候报错`reader raised an exception`，但是具体不知道是啥问题？ **A**：这个一般是因为标注文件格式有问题或者是标注文件中的图片路径有问题导致的，在[tools/train.py](../../tools/train.py)文件中有一个`test_reader`的函数，基于这个去检查一下数据的格式以及标注，确认没问题之后再进行模型训练。 @@ -390,6 +388,10 @@ **A**：PaddleOCR主要聚焦通用ocr，如果有垂类需求，您可以用PaddleOCR+垂类数据自己训练； 如果缺少带标注的数据，或者不想投入研发成本，建议直接调用开放的API，开放的API覆盖了目前比较常见的一些垂类。 +#### Q3.1.21：PaddleOCR支持动态图吗？ + +**A**：动态图版本正在紧锣密鼓开发中，将于2020年12月16日发布，敬请关注。 + ### 数据集 @@ -603,6 +605,18 @@ ps -axu | grep train.py | awk '{print $2}' | xargs kill -9 **A**: 识别修改[这里](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yaml#L75) , 检测修改[这里](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml#L85) +#### Q3.3.23：检测模型训练或预测时出现elementwise_add报错 + +**A**：设置的输入尺寸必须是32的倍数，否则在网络多次下采样和上采样后，feature map会产生1个像素的diff，从而导致elementwise_add时报shape不匹配的错误。 + +#### Q3.3.24: DB检测训练输入尺寸640，可以改大一些吗？ + +**A**: 不建议改大。检测模型训练输入尺寸是预处理中random crop后的尺寸，并非直接将原图进行resize，多数场景下这个尺寸并不小了，改大后可能反而并不合适，而且训练会变慢。另外，代码里可能有的地方参数按照预设输入尺寸适配的，改大后可能有隐藏风险。 + +#### Q3.3.25: 识别模型训练时，loss能正常下降，但acc一直为0 + +**A**: 识别模型训练初期acc为0是正常的，多训一段时间指标就上来了。 + ### 预测部署 @@ -710,4 +724,8 @@ ps -axu | grep train.py | awk '{print $2}' | xargs kill -9 #### Q3.4.23：安装paddleocr后，提示没有paddle -**A**：这是因为paddlepaddle gpu版本和cpu版本的名称不一致，现在已经在[whl的文档](./whl.md)里做了安装说明。 \ No newline at end of file +**A**：这是因为paddlepaddle gpu版本和cpu版本的名称不一致，现在已经在[whl的文档](./whl.md)里做了安装说明。 + +#### Q3.4.24：DB模型能正确推理预测，但换成EAST或SAST模型时报错或结果不正确 + +**A**：使用EAST或SAST模型进行推理预测时，需要在命令中指定参数--det_algorithm="EAST" 或 --det_algorithm="SAST"，使用DB时不用指定是因为该参数默认值是"DB"：https://github.com/PaddlePaddle/PaddleOCR/blob/e7a708e9fdaf413ed7a14da8e4a7b4ac0b211e42/tools/infer/utility.py#L43 \ No newline at end of file diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md index aea7ff1de242dec75cae26a2bf3d6838d7559882..09303e93534b091ee50cb6d62045b95faee6cfe5 100755 --- a/doc/doc_ch/inference.md +++ b/doc/doc_ch/inference.md @@ -131,12 +131,12 @@ python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o Global.pretrained_mo # 下载超轻量中文检测模型： 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 -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/22.jpg" --det_model_dir="./ch_ppocr_mobile_v2.0_det_infer/" +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_ppocr_mobile_v2.0_det_infer/" ``` 可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下： -![](../imgs_results/det_res_22.jpg) +![](../imgs_results/det_res_00018069.jpg) 通过参数`limit_type`和`det_limit_side_len`来对图片的尺寸进行限制， `litmit_type`可选参数为[`max`, `min`]， diff --git a/doc/doc_ch/installation.md b/doc/doc_ch/installation.md index 0dddfec0a6e17e26a73d284ac98c9c95e449c378..36565cd4197a9b8b8404f57b378aa49637cdc58b 100644 --- a/doc/doc_ch/installation.md +++ b/doc/doc_ch/installation.md @@ -58,7 +58,7 @@ git clone https://gitee.com/paddlepaddle/PaddleOCR **4. 安装第三方库** ``` cd PaddleOCR -pip3 install -r requirments.txt +pip3 install -r requirements.txt ``` 注意，windows环境下，建议从[这里](https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely)下载shapely安装包完成安装， diff --git a/doc/doc_ch/tree.md b/doc/doc_ch/tree.md index 511860869188020ccfe7531db55ecc5008ccb56b..5f048db022dbe422a78f87b0236d04e00ccc4d48 100644 --- a/doc/doc_ch/tree.md +++ b/doc/doc_ch/tree.md @@ -115,7 +115,7 @@ PaddleOCR │ │ │ ├── text_image_aug // 文本识别的 tia 数据扩充 │ │ │ │ ├── __init__.py │ │ │ │ ├── augment.py // tia_distort,tia_stretch 和 tia_perspective 的代码 -│ │ │ │ ├── warp_mls.py +│ │ │ │ ├── warp_mls.py │ │ │ ├── __init__.py │ │ │ ├── east_process.py // EAST 算法的数据处理步骤 │ │ │ ├── make_border_map.py // 生成边界图 @@ -167,7 +167,7 @@ PaddleOCR │ │ │ ├── det_east_head.py // EAST 检测头 │ │ │ ├── det_sast_head.py // SAST 检测头 │ │ │ ├── rec_ctc_head.py // 识别 ctc -│ │ │ ├── rec_att_head.py // 识别 attention +│ │ │ ├── rec_att_head.py // 识别 attention │ │ ├── transforms // 图像变换 │ │ │ ├── __init__.py // 构造 transform 相关代码 │ │ │ └── tps.py // TPS 变换 @@ -185,7 +185,7 @@ PaddleOCR │ │ └── sast_postprocess.py // SAST 后处理 │ └── utils // 工具 │ ├── dict // 小语种字典 -│ .... +│ .... │ ├── ic15_dict.txt // 英文数字字典，区分大小写 │ ├── ppocr_keys_v1.txt // 中文字典，用于训练中文模型 │ ├── logging.py // logger @@ -207,10 +207,10 @@ PaddleOCR │ ├── program.py // 整体流程 │ ├── test_hubserving.py │ └── train.py // 启动训练 -├── paddleocr.py +├── paddleocr.py ├── README_ch.md // 中文说明文档 ├── README_en.md // 英文说明文档 ├── README.md // 主页说明文档 -├── requirments.txt // 安装依赖 +├── requirements.txt // 安装依赖 ├── setup.py // whl包打包脚本 -├── train.sh // 启动训练脚本 \ No newline at end of file +├── train.sh // 启动训练脚本 diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md index db86b109d1a13d00aab833aa31d0279622e7c7f8..3fcd36c076c7d969420818484034ed610e76bc27 100755 --- a/doc/doc_en/inference_en.md +++ b/doc/doc_en/inference_en.md @@ -138,12 +138,12 @@ For lightweight Chinese detection model inference, you can execute the following 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 # predict -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/22.jpg" --det_model_dir="./inference/det_db/" +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" ``` The visual 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: -![](../imgs_results/det_res_22.jpg) +![](../imgs_results/det_res_00018069.jpg) You can use the parameters `limit_type` and `det_limit_side_len` to limit the size of the input image, The optional parameters of `litmit_type` are [`max`, `min`], and diff --git a/doc/doc_en/installation_en.md b/doc/doc_en/installation_en.md index 073b67b04d10cc2ae4b20f0ca38b604ab95bc09f..7f1f0e83c94e4d4a18b99d620b4b192c47ffde7c 100644 --- a/doc/doc_en/installation_en.md +++ b/doc/doc_en/installation_en.md @@ -61,7 +61,7 @@ git clone https://gitee.com/paddlepaddle/PaddleOCR **4. Install third-party libraries** ``` cd PaddleOCR -pip3 install -r requirments.txt +pip3 install -r requirements.txt ``` If you getting this error `OSError: [WinError 126] The specified module could not be found` when you install shapely on windows. diff --git a/doc/doc_en/tree_en.md b/doc/doc_en/tree_en.md index be2f5733d3c30af8c83f1072cd0aea07865bacc3..cf9ccb38dcc0e5f70577f18933a5373d1ffa992a 100644 --- a/doc/doc_en/tree_en.md +++ b/doc/doc_en/tree_en.md @@ -116,7 +116,7 @@ PaddleOCR │ │ │ ├── text_image_aug // Tia data augment for text recognition │ │ │ │ ├── __init__.py │ │ │ │ ├── augment.py // Tia_distort,tia_stretch and tia_perspective -│ │ │ │ ├── warp_mls.py +│ │ │ │ ├── warp_mls.py │ │ │ ├── __init__.py │ │ │ ├── east_process.py // Data processing steps of EAST algorithm │ │ │ ├── iaa_augment.py // Data augmentation operations @@ -188,7 +188,7 @@ PaddleOCR │ │ └── sast_postprocess.py // SAST post-processing │ └── utils // utils │ ├── dict // Minor language dictionary -│ .... +│ .... │ ├── ic15_dict.txt // English number dictionary, case sensitive │ ├── ppocr_keys_v1.txt // Chinese dictionary for training Chinese models │ ├── logging.py // logger @@ -210,10 +210,10 @@ PaddleOCR │ ├── program.py // Inference system │ ├── test_hubserving.py │ └── train.py // Start training script -├── paddleocr.py +├── paddleocr.py ├── README_ch.md // Chinese documentation ├── README_en.md // English documentation ├── README.md // Home page documentation -├── requirments.txt // Requirments +├── requirements.txt // Requirements ├── setup.py // Whl package packaging script -├── train.sh // Start training bash script \ No newline at end of file +├── train.sh // Start training bash script diff --git a/doc/imgs/00006737.jpg b/doc/imgs/00006737.jpg new file mode 100755 index 0000000000000000000000000000000000000000..5c3329a8a0e64cb251cb5f6719d177146e75b866 Binary files /dev/null and b/doc/imgs/00006737.jpg differ diff --git a/doc/imgs/00009282.jpg b/doc/imgs/00009282.jpg new file mode 100755 index 0000000000000000000000000000000000000000..448d0f11209f4328e4097777007fdff97efbee7b Binary files /dev/null and b/doc/imgs/00009282.jpg differ diff --git a/doc/imgs/00015504.jpg b/doc/imgs/00015504.jpg new file mode 100755 index 0000000000000000000000000000000000000000..9d6aaee181913ef0d6c82b1728bc71de3130a804 Binary files /dev/null and b/doc/imgs/00015504.jpg differ diff --git a/doc/imgs/00018069.jpg b/doc/imgs/00018069.jpg new file mode 100755 index 0000000000000000000000000000000000000000..e768d8adfc5882ffac6e332ce858a175dd4a5bb7 Binary files /dev/null and b/doc/imgs/00018069.jpg differ diff --git a/doc/imgs/00056221.jpg b/doc/imgs/00056221.jpg new file mode 100755 index 0000000000000000000000000000000000000000..698e0dfc5334d64536bf9211fb2edcb5ed429186 Binary files /dev/null and b/doc/imgs/00056221.jpg differ diff --git a/doc/imgs/00057937.jpg b/doc/imgs/00057937.jpg new file mode 100755 index 0000000000000000000000000000000000000000..82a45c47bb87934ecdf599c4339de103ab965277 Binary files /dev/null and b/doc/imgs/00057937.jpg differ diff --git a/doc/imgs/00059985.jpg b/doc/imgs/00059985.jpg new file mode 100755 index 0000000000000000000000000000000000000000..0b5b656a160dfebe355e5ad58639de1170845e3f Binary files /dev/null and b/doc/imgs/00059985.jpg differ diff --git a/doc/imgs/00077949.jpg b/doc/imgs/00077949.jpg new file mode 100755 index 0000000000000000000000000000000000000000..1f832d7903e26a89148e18724d0561b926508cc7 Binary files /dev/null and b/doc/imgs/00077949.jpg differ diff --git a/doc/imgs/00111002.jpg b/doc/imgs/00111002.jpg new file mode 100755 index 0000000000000000000000000000000000000000..2aae5f7cb8829429d1564a345aa726ad426b6ec0 Binary files /dev/null and b/doc/imgs/00111002.jpg differ diff --git a/doc/imgs/00207393.jpg b/doc/imgs/00207393.jpg new file mode 100755 index 0000000000000000000000000000000000000000..e278adfb5973e44a437689a92ffac3ea882a5164 Binary files /dev/null and b/doc/imgs/00207393.jpg differ diff --git a/doc/imgs/10.jpg b/doc/imgs/10.jpg deleted file mode 100755 index a73e25dbdcdc30135804104934f5aae491d43ca8..0000000000000000000000000000000000000000 Binary files a/doc/imgs/10.jpg and /dev/null differ diff --git a/doc/imgs/13.png b/doc/imgs/13.png deleted file mode 100644 index 16e931ac69c7c99b813947c444b4a0be648b46d8..0000000000000000000000000000000000000000 Binary files a/doc/imgs/13.png and /dev/null differ diff --git a/doc/imgs/15.jpg b/doc/imgs/15.jpg deleted file mode 100644 index 180dcac005f28edae5b91fe9d99f05bd8471856a..0000000000000000000000000000000000000000 Binary files a/doc/imgs/15.jpg and /dev/null differ diff --git a/doc/imgs/16.png b/doc/imgs/16.png deleted file mode 100644 index a1adf38cd185b8a650c18226556ec0ba7a2a17f6..0000000000000000000000000000000000000000 Binary files a/doc/imgs/16.png and /dev/null differ diff --git a/doc/imgs/17.png b/doc/imgs/17.png deleted file mode 100644 index 0415adf59f9a2a65aa8ddb9c781ce01b643f5224..0000000000000000000000000000000000000000 Binary files a/doc/imgs/17.png and /dev/null differ diff --git a/doc/imgs/2.jpg b/doc/imgs/2.jpg deleted file mode 100644 index 811d2450e0a98bcfcef6980b08e6082d4f468bcf..0000000000000000000000000000000000000000 Binary files a/doc/imgs/2.jpg and /dev/null differ diff --git a/doc/imgs/22.jpg b/doc/imgs/22.jpg deleted file mode 100644 index 9bd1129d6724abc2fb541189df148c5c14721c64..0000000000000000000000000000000000000000 Binary files a/doc/imgs/22.jpg and /dev/null differ diff --git a/doc/imgs/3.jpg b/doc/imgs/3.jpg deleted file mode 100644 index 3bd6ca2bdacbdf63cf151ae4b1bab41688379510..0000000000000000000000000000000000000000 Binary files a/doc/imgs/3.jpg and /dev/null differ diff --git a/doc/imgs/4.jpg b/doc/imgs/4.jpg deleted file mode 100755 index 9669f7780d7eb9072b0befa2d043e55be9dcce1f..0000000000000000000000000000000000000000 Binary files a/doc/imgs/4.jpg and /dev/null differ diff --git a/doc/imgs/5.jpg b/doc/imgs/5.jpg deleted file mode 100644 index 8517e125c5e660f1bc603a844f946c68086e4616..0000000000000000000000000000000000000000 Binary files a/doc/imgs/5.jpg and /dev/null differ diff --git a/doc/imgs/6.jpg b/doc/imgs/6.jpg deleted file mode 100644 index 2705e262b337e565f0cbdde0914c6ef41275ebba..0000000000000000000000000000000000000000 Binary files a/doc/imgs/6.jpg and /dev/null differ diff --git a/doc/imgs/7.jpg b/doc/imgs/7.jpg deleted file mode 100644 index a9483bb74f66d88699b09545366c32a4fe108e54..0000000000000000000000000000000000000000 Binary files a/doc/imgs/7.jpg and /dev/null differ diff --git a/doc/imgs/8.jpg b/doc/imgs/8.jpg deleted file mode 100755 index 8dabd03f577ba7a510647304ca1c60e51fb6e65c..0000000000000000000000000000000000000000 Binary files a/doc/imgs/8.jpg and /dev/null differ diff --git a/doc/imgs/9.jpg b/doc/imgs/9.jpg deleted file mode 100644 index 8633c6d2dc25a73c31ec1164fe6c651497295977..0000000000000000000000000000000000000000 Binary files a/doc/imgs/9.jpg and /dev/null differ diff --git a/doc/imgs_results/2.jpg b/doc/imgs_results/2.jpg deleted file mode 100644 index 99f7e63b02556506dadf8d838eee22534d21d82c..0000000000000000000000000000000000000000 Binary files a/doc/imgs_results/2.jpg and /dev/null differ diff --git a/doc/imgs_results/det_res_00018069.jpg b/doc/imgs_results/det_res_00018069.jpg new file mode 100644 index 0000000000000000000000000000000000000000..02f35de332cb15594404c6a7df100f7b80e7c410 Binary files /dev/null and b/doc/imgs_results/det_res_00018069.jpg differ diff --git a/doc/imgs_results/det_res_2.jpg b/doc/imgs_results/det_res_2.jpg deleted file mode 100644 index c0ae501a7aff7807f53b743745005653775b0d03..0000000000000000000000000000000000000000 Binary files a/doc/imgs_results/det_res_2.jpg and /dev/null differ diff --git a/doc/imgs_results/det_res_22.jpg b/doc/imgs_results/det_res_22.jpg deleted file mode 100644 index d1255f49d9d371d4b91d98c6750a10a01f56b629..0000000000000000000000000000000000000000 Binary files a/doc/imgs_results/det_res_22.jpg and /dev/null differ diff --git a/ppocr/losses/det_db_loss.py b/ppocr/losses/det_db_loss.py index f170f6734a19289305a41d9e3f17a51d5ad10ec7..b079aabff7c7deccc7e365b91c9407f7e894bcb9 100755 --- a/ppocr/losses/det_db_loss.py +++ b/ppocr/losses/det_db_loss.py @@ -47,11 +47,12 @@ class DBLoss(nn.Layer): negative_ratio=ohem_ratio) def forward(self, predicts, labels): + predict_maps = predicts['maps'] label_threshold_map, label_threshold_mask, label_shrink_map, label_shrink_mask = labels[ 1:] - shrink_maps = predicts[:, 0, :, :] - threshold_maps = predicts[:, 1, :, :] - binary_maps = predicts[:, 2, :, :] + shrink_maps = predict_maps[:, 0, :, :] + threshold_maps = predict_maps[:, 1, :, :] + binary_maps = predict_maps[:, 2, :, :] loss_shrink_maps = self.bce_loss(shrink_maps, label_shrink_map, label_shrink_mask) diff --git a/ppocr/modeling/heads/det_db_head.py b/ppocr/modeling/heads/det_db_head.py index 49c50ffdba89f557e71ac5c7abe4e07e52bc9119..ca18d74a68f7b17ee6383d4a0c995a4c46a16187 100644 --- a/ppocr/modeling/heads/det_db_head.py +++ b/ppocr/modeling/heads/det_db_head.py @@ -120,9 +120,9 @@ class DBHead(nn.Layer): def forward(self, x): shrink_maps = self.binarize(x) if not self.training: - return shrink_maps + return {'maps': shrink_maps} threshold_maps = self.thresh(x) binary_maps = self.step_function(shrink_maps, threshold_maps) y = paddle.concat([shrink_maps, threshold_maps, binary_maps], axis=1) - return y + return {'maps': y} diff --git a/ppocr/postprocess/db_postprocess.py b/ppocr/postprocess/db_postprocess.py index 16c789dcd7e9740ca8ddf613d0f2567c9af22820..91729e0a93c8b013cd734abc37cb6ac2b4960312 100755 --- a/ppocr/postprocess/db_postprocess.py +++ b/ppocr/postprocess/db_postprocess.py @@ -40,7 +40,8 @@ class DBPostProcess(object): self.max_candidates = max_candidates self.unclip_ratio = unclip_ratio self.min_size = 3 - self.dilation_kernel = None if not use_dilation else np.array([[1, 1], [1, 1]]) + self.dilation_kernel = None if not use_dilation else np.array( + [[1, 1], [1, 1]]) def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height): ''' @@ -132,7 +133,8 @@ class DBPostProcess(object): cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1) return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0] - def __call__(self, pred, shape_list): + def __call__(self, outs_dict, shape_list): + pred = outs_dict['maps'] if isinstance(pred, paddle.Tensor): pred = pred.numpy() pred = pred[:, 0, :, :] diff --git a/ppocr/utils/save_load.py b/ppocr/utils/save_load.py index af2de054de3656638fee8d4328765c21b4deaea4..02814d6208aba7ddfa6eac338229502b18b535da 100644 --- a/ppocr/utils/save_load.py +++ b/ppocr/utils/save_load.py @@ -102,7 +102,6 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None): best_model_dict = states_dict.get('best_model_dict', {}) if 'epoch' in states_dict: best_model_dict['start_epoch'] = states_dict['epoch'] + 1 - best_model_dict['start_epoch'] = best_model_dict['best_epoch'] + 1 logger.info("resume from {}".format(checkpoints)) elif pretrained_model: diff --git a/tools/infer/predict_det.py b/tools/infer/predict_det.py index d389ca393dc94a7ece69e6f59f999073ae4b1773..ba0adaee258096ea9970425cc05ca7a8f1cf08c4 100755 --- a/tools/infer/predict_det.py +++ b/tools/infer/predict_det.py @@ -65,12 +65,12 @@ class TextDetector(object): postprocess_params["unclip_ratio"] = args.det_db_unclip_ratio postprocess_params["use_dilation"] = True elif self.det_algorithm == "EAST": - postprocess_params['name'] = 'EASTPostProcess' + postprocess_params['name'] = 'EASTPostProcess' postprocess_params["score_thresh"] = args.det_east_score_thresh postprocess_params["cover_thresh"] = args.det_east_cover_thresh postprocess_params["nms_thresh"] = args.det_east_nms_thresh elif self.det_algorithm == "SAST": - postprocess_params['name'] = 'SASTPostProcess' + postprocess_params['name'] = 'SASTPostProcess' postprocess_params["score_thresh"] = args.det_sast_score_thresh postprocess_params["nms_thresh"] = args.det_sast_nms_thresh self.det_sast_polygon = args.det_sast_polygon @@ -177,8 +177,10 @@ class TextDetector(object): preds['f_score'] = outputs[1] preds['f_tco'] = outputs[2] preds['f_tvo'] = outputs[3] + elif self.det_algorithm == 'DB': + preds['maps'] = outputs[0] else: - preds = outputs[0] + raise NotImplementedError post_result = self.postprocess_op(preds, shape_list) dt_boxes = post_result[0]['points']