From a3efb541ebf173c8197f3b62c7821ba84f3a1ffb Mon Sep 17 00:00:00 2001 From: MissPenguin Date: Thu, 4 Aug 2022 06:55:50 +0000 Subject: [PATCH] refine doc --- applications/README.md | 2 +- ...\226\207\350\257\206\345\210\253\346\250\241\345\236\213.md" | 2 +- doc/doc_ch/PP-OCRv3_introduction.md | 2 +- doc/doc_en/PP-OCRv3_introduction_en.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/applications/README.md b/applications/README.md index 6061f202..017c2a9f 100644 --- a/applications/README.md +++ b/applications/README.md @@ -22,7 +22,7 @@ PaddleOCR场景应用覆盖通用,制造、金融、交通行业的主要OCR | 类别 | 亮点 | 模型下载 | 教程 | | ---------------------- | ------------ | -------------- | --------------------------------------- | -| 高精度中文识别模型SVTR | 新增模型 | [模型下载](#2) | [中文](./高精度中文识别模型.md)/English | +| 高精度中文识别模型SVTR | 比PP-OCRv3识别模型精度高3%,可用于数据挖掘或对预测效率要求不高的场景。| [模型下载](#2) | [中文](./高精度中文识别模型.md)/English | | 手写体识别 | 新增字形支持 | | | diff --git "a/applications/\351\253\230\347\262\276\345\272\246\344\270\255\346\226\207\350\257\206\345\210\253\346\250\241\345\236\213.md" "b/applications/\351\253\230\347\262\276\345\272\246\344\270\255\346\226\207\350\257\206\345\210\253\346\250\241\345\236\213.md" index 3c31af42..4e71e233 100644 --- "a/applications/\351\253\230\347\262\276\345\272\246\344\270\255\346\226\207\350\257\206\345\210\253\346\250\241\345\236\213.md" +++ "b/applications/\351\253\230\347\262\276\345\272\246\344\270\255\346\226\207\350\257\206\345\210\253\346\250\241\345\236\213.md" @@ -2,7 +2,7 @@ ## 1. 简介 -PP-OCRv3是百度开源的超轻量级场景文本检测识别模型库,其中超轻量的场景中文识别模型SVTR_LCNet使用了SVTR算法结构。为了保证速度,SVTR_LCNet将SVTR模型的Local Blocks替换为LCNet,使用两层Global Blocks。在中文场景中,PP-OCRv3识别主要使用如下优化策略: +PP-OCRv3是百度开源的超轻量级场景文本检测识别模型库,其中超轻量的场景中文识别模型SVTR_LCNet使用了SVTR算法结构。为了保证速度,SVTR_LCNet将SVTR模型的Local Blocks替换为LCNet,使用两层Global Blocks。在中文场景中,PP-OCRv3识别主要使用如下优化策略([详细技术报告](../doc/doc_ch/PP-OCRv3_introduction.md)): - GTC:Attention指导CTC训练策略; - TextConAug:挖掘文字上下文信息的数据增广策略; - TextRotNet:自监督的预训练模型; diff --git a/doc/doc_ch/PP-OCRv3_introduction.md b/doc/doc_ch/PP-OCRv3_introduction.md index b8a6ad12..ddeb78d7 100644 --- a/doc/doc_ch/PP-OCRv3_introduction.md +++ b/doc/doc_ch/PP-OCRv3_introduction.md @@ -185,7 +185,7 @@ UDML(Unified-Deep Mutual Learning)联合互学习是PP-OCRv2中就采用的 **(6)UIM:无标注数据挖掘方案** -UIM(Unlabeled Images Mining)是一种非常简单的无标注数据挖掘方案。核心思想是利用高精度的文本识别大模型对无标注数据进行预测,获取伪标签,并且选择预测置信度高的样本作为训练数据,用于训练小模型。使用该策略,识别模型的准确率进一步提升到79.4%(+1%)。 +UIM(Unlabeled Images Mining)是一种非常简单的无标注数据挖掘方案。核心思想是利用高精度的文本识别大模型对无标注数据进行预测,获取伪标签,并且选择预测置信度高的样本作为训练数据,用于训练小模型。使用该策略,识别模型的准确率进一步提升到79.4%(+1%)。实际操作中,我们使用全量数据集训练高精度SVTR-Tiny模型(acc=82.5%)进行数据挖掘,点击获取[模型下载地址和使用教程](../../applications/高精度中文识别模型.md)。
diff --git a/doc/doc_en/PP-OCRv3_introduction_en.md b/doc/doc_en/PP-OCRv3_introduction_en.md index baa6c9be..815ad9b0 100644 --- a/doc/doc_en/PP-OCRv3_introduction_en.md +++ b/doc/doc_en/PP-OCRv3_introduction_en.md @@ -200,7 +200,7 @@ UDML (Unified-Deep Mutual Learning) is a strategy proposed in PP-OCRv2 which is **(6)UIM:Unlabeled Images Mining** -UIM (Unlabeled Images Mining) is a very simple unlabeled data mining strategy. The main idea is to use a high-precision text recognition model to predict unlabeled images to obtain pseudo-labels, and select samples with high prediction confidence as training data for training lightweight models. Using this strategy, the accuracy of the recognition model is further improved to 79.4% (+1%). +UIM (Unlabeled Images Mining) is a very simple unlabeled data mining strategy. The main idea is to use a high-precision text recognition model to predict unlabeled images to obtain pseudo-labels, and select samples with high prediction confidence as training data for training lightweight models. Using this strategy, the accuracy of the recognition model is further improved to 79.4% (+1%). In practice, we use the full data set to train the high-precision SVTR_Tiny model (acc=82.5%) for data mining. [SVTR_Tiny model download and tutorial](../../applications/高精度中文识别模型.md).
-- GitLab