diff --git a/README.md b/README.md index d27d22b75fa006f2f210246a0865838fe3b711a2..ee7cee80620db58bb4bc400144015ac41f3b7655 100644 --- a/README.md +++ b/README.md @@ -90,7 +90,7 @@ Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Andr | Model introduction | Model name | Recommended scene | Detection model | Direction classifier | Recognition model | | ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | -| 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/ch/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/dygraph_v2.1/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 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_traingit.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) | diff --git a/deploy/pdserving/README.md b/deploy/pdserving/README.md index c461fd5e54d3a51ad3427f83a1fca35cbe3ab2d8..2b5a422444d7bedaa69773fbc678f292f5d0e684 100644 --- a/deploy/pdserving/README.md +++ b/deploy/pdserving/README.md @@ -201,7 +201,7 @@ The recognition model is the same. ## WINDOWS Users -Windows does not support Pipeline Serving, if we want to lauch paddle serving on Windows, we should use Web Service, for more infomation please refer to [Paddle Serving for Windows Users](https://github.com/PaddlePaddle/Serving/blob/develop/doc/WINDOWS_TUTORIAL.md) +Windows does not support Pipeline Serving, if we want to lauch paddle serving on Windows, we should use Web Service, for more infomation please refer to [Paddle Serving for Windows Users](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Windows_Tutorial_EN.md) **WINDOWS user can only use version 0.5.0 CPU Mode** diff --git a/deploy/pdserving/README_CN.md b/deploy/pdserving/README_CN.md index 00024639b0b108225a0835499f62174b6618ae47..766c15181f2457b4a16a83a105cfa41de3c96cf3 100644 --- a/deploy/pdserving/README_CN.md +++ b/deploy/pdserving/README_CN.md @@ -189,7 +189,7 @@ python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \ ## WINDOWS用户 -Windows用户不能使用上述的启动方式,需要使用Web Service,详情参见[Windows平台使用Paddle Serving指导](https://github.com/PaddlePaddle/Serving/blob/develop/doc/WINDOWS_TUTORIAL_CN.md) +Windows用户不能使用上述的启动方式,需要使用Web Service,详情参见[Windows平台使用Paddle Serving指导](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Windows_Tutorial_CN.md) **WINDOWS只能使用0.5.0版本的CPU模式** diff --git a/doc/doc_ch/data_synthesis.md b/doc/doc_ch/data_synthesis.md index a5b9c4aca0bd5a0795b297c31161717aff2c298b..8c43ac2e3b2b13f14c747482f854c81e544f6272 100644 --- a/doc/doc_ch/data_synthesis.md +++ b/doc/doc_ch/data_synthesis.md @@ -1,4 +1,4 @@ -## 数据合成工具 +# 数据合成工具 除了开源数据,用户还可使用合成工具自行合成。这里整理了常用的数据合成工具,持续更新中,欢迎各位小伙伴贡献工具~ - [text_renderer](https://github.com/Sanster/text_renderer) - [SynthText](https://github.com/ankush-me/SynthText) @@ -6,3 +6,4 @@ - [TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator) - [SynthText3D](https://github.com/MhLiao/SynthText3D) - [UnrealText](https://github.com/Jyouhou/UnrealText/) +- [SynthTIGER](https://github.com/clovaai/synthtiger) \ No newline at end of file diff --git a/doc/doc_ch/enhanced_ctc_loss.md b/doc/doc_ch/enhanced_ctc_loss.md index 8c0856a7a7bceedbcc0a48bb1af6658afa720886..bf4d4c37bb68b4609b1da31507f700e0f569594e 100644 --- a/doc/doc_ch/enhanced_ctc_loss.md +++ b/doc/doc_ch/enhanced_ctc_loss.md @@ -1,10 +1,11 @@ # Enhanced CTC Loss -在OCR识别中, CRNN是一种在工业界广泛使用的文字识别算法。 在训练阶段,其采用CTCLoss来计算网络损失; 在推理阶段,其采用CTCDecode来获得解码结果。虽然CRNN算法在实际业务中被证明能够获得很好的识别效果, 然而用户对识别准确率的要求却是无止境的,如何进一步提升文字识别的准确率呢? 本文以CTCLoss为切人点,分别从难例挖掘、 多任务学习、 Metric Learning 3个不同的角度探索了CTCLoss的改进融合方案,提出了EnhancedCTCLoss,其包括如下3个组成部分: Focal-CTC Loss,A-CTC Loss, C-CTC Loss。 +在OCR识别中, CRNN是一种在工业界广泛使用的文字识别算法。 在训练阶段,其采用CTCLoss来计算网络损失; 在推理阶段,其采用CTCDecode来获得解码结果。虽然CRNN算法在实际业务中被证明能够获得很好的识别效果, 然而用户对识别准确率的要求却是无止境的,如何进一步提升文字识别的准确率呢? 本文以CTCLoss为切入点,分别从难例挖掘(Hard Example Mining)、 多任务学习(Multi-task Learning)、 度量学习(Metric Learning)3个不同的角度探索了CTCLoss的改进融合方案,提出了EnhancedCTCLoss,其包括如下3个组成部分: Focal-CTC Loss,A-CTC Loss, C-CTC Loss。 ## 1. Focal-CTC Loss -Focal Loss 出自论文《Focal Loss for Dense Object Detection》, 该loss最先提出的时候主要是为了解决one-stage目标检测中正负样本比例严重失衡的问题。该损失函数降低了大量简单负样本在训练中所占的权重,也可理解为一种困难样本挖掘。 +Focal Loss 出自论文《[Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002)》, 该loss最先提出的时候主要是为了解决one-stage目标检测中正负样本比例严重失衡的问题。该损失函数降低了大量简单负样本在训练中所占的权重,也可理解为一种困难样本挖掘。 其损失函数形式如下: +