From e2b2f33092874afe860b324450b49ea8bd8bc5f4 Mon Sep 17 00:00:00 2001 From: andyjpaddle Date: Mon, 30 May 2022 09:25:21 +0000 Subject: [PATCH] update some note --- deploy/cpp_infer/readme.md | 2 +- deploy/cpp_infer/readme_ch.md | 2 +- doc/doc_ch/quickstart.md | 2 +- doc/doc_en/quickstart_en.md | 2 +- paddleocr.py | 8 +++++++- 5 files changed, 11 insertions(+), 5 deletions(-) diff --git a/deploy/cpp_infer/readme.md b/deploy/cpp_infer/readme.md index 942a633f..a87db7e6 100644 --- a/deploy/cpp_infer/readme.md +++ b/deploy/cpp_infer/readme.md @@ -208,7 +208,7 @@ Execute the built executable file: ./build/ppocr [--param1] [--param2] [...] ``` -**Note**:ppocr uses the `PP-OCRv3` model by default, and the input shape used by the recognition model is `3, 48, 320`, if you do not use the default `PP-OCRv3` model, you should add the parameter `--rec_img_h=32`. +**Note**:ppocr uses the `PP-OCRv3` model by default, and the input shape used by the recognition model is `3, 48, 320`, if you want to use the old version model, you should add the parameter `--rec_img_h=32`. Specifically, diff --git a/deploy/cpp_infer/readme_ch.md b/deploy/cpp_infer/readme_ch.md index 4a79f978..8c334851 100644 --- a/deploy/cpp_infer/readme_ch.md +++ b/deploy/cpp_infer/readme_ch.md @@ -213,7 +213,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir 本demo支持系统串联调用，也支持单个功能的调用，如，只使用检测或识别功能。 -**注意** ppocr默认使用`PP-OCRv3`模型，识别模型使用的输入shape为`3,48,320`, 如果不使用默认的`PP-OCRv3`模型，则需要设置参数`--rec_img_h=32`。 +**注意** ppocr默认使用`PP-OCRv3`模型，识别模型使用的输入shape为`3,48,320`, 如需使用旧版本的PP-OCR模型，则需要设置参数`--rec_img_h=32`。 运行方式： diff --git a/doc/doc_ch/quickstart.md b/doc/doc_ch/quickstart.md index d2c2f288..e425cdd8 100644 --- a/doc/doc_ch/quickstart.md +++ b/doc/doc_ch/quickstart.md @@ -106,7 +106,7 @@ paddleocr默认使用PP-OCRv3模型(`--ocr_version PP-OCRv3`)，如需使用其 | 版本名称 | 版本说明 | | --- | --- | | PP-OCRv3 | 支持中、英文检测和识别，方向分类器，支持多语种识别 | -| PP-OCRv2 | 仅支持中英文的检测和识别 | +| PP-OCRv2 | 支持中英文的检测和识别，方向分类器，多语言暂未更新 | | PP-OCR | 支持中、英文检测和识别，方向分类器，支持多语种识别 | 如需新增自己训练的模型，可以在[paddleocr](../../paddleocr.py)中增加模型链接和字段，重新编译即可。 diff --git a/doc/doc_en/quickstart_en.md b/doc/doc_en/quickstart_en.md index f0e41e31..c678dc47 100644 --- a/doc/doc_en/quickstart_en.md +++ b/doc/doc_en/quickstart_en.md @@ -124,7 +124,7 @@ paddleocr uses the PP-OCRv3 model by default(`--ocr_version PP-OCRv3`). If you w | version name | description | | --- | --- | | PP-OCRv3 | support Chinese and English detection and recognition, direction classifier, support multilingual recognition | -| PP-OCRv2 | only supports Chinese and English detection and recognition | +| PP-OCRv2 | only supports Chinese and English detection and recognition, direction classifier, multilingual model is not updated | | PP-OCR | support Chinese and English detection and recognition, direction classifier, support multilingual recognition | If you want to add your own trained model, you can add model links and keys in [paddleocr](../../paddleocr.py) and recompile. diff --git a/paddleocr.py b/paddleocr.py index a1265f79..470dc60d 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -154,7 +154,13 @@ MODEL_URLS = { 'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar', 'dict_path': './ppocr/utils/ppocr_keys_v1.txt' } - } + }, + 'cls': { + 'ch': { + 'url': + 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar', + } + }, }, 'PP-OCR': { 'det': { -- GitLab