Skip to content

Commit

Permalink
deploy: a263cb4
Browse files Browse the repository at this point in the history
  • Loading branch information
SWHL committed Jan 30, 2024
1 parent fda6163 commit 2878833
Show file tree
Hide file tree
Showing 52 changed files with 245 additions and 245 deletions.
6 changes: 3 additions & 3 deletions docs/about_model/convert_model/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/about_model/index.html

Large diffs are not rendered by default.

24 changes: 12 additions & 12 deletions docs/about_model/model_summary/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/about_model/support_language/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/01_optim_tutorial/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/02_config_parameter/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/03_which_inference/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/04_inference_summary/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/05_rec_dict_onnx/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/06_custom_different_model/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/blog/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/business_support/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/changelog/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/changelog/rapidocr/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/changelog/rapidocr_api/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/changelog/rapidocr_paddle/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/changelog/rapidocr_web/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/communicate/index.html

Large diffs are not rendered by default.

24 changes: 12 additions & 12 deletions docs/faq/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/index.html

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion docs/index.xml
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@
<pubDate>Sun, 02 Oct 2022 00:00:00 +0000</pubDate>

<guid>https://rapidai.github.io/RapidOCRDocs/docs/faq/</guid>
<description>Q: 为什么我的模型在GPU上比在CPU上还要慢? linkA: : 取决于所使用的执行提供者,它可能没有完全支持模型中的所有操作。回落到CPU操作可能会导致性能速度的下降。此外,即使一个操作是由CUDA execution provider实现的,由于性能的原因,它也不一定会把操作分配/放置到CUDA EP上。要想看到ORT决定的位置,请打开verbose日志并查看控制台的输出
<description>Q: 为什么我的模型在ONNXRuntime GPU版上比在CPU上还要慢? linkA: : 因为OCR任务中输入图像Shape是动态的。每次GPU上都需要重新清空上一次不同Shape的缓存结果。如果输入图像Shape不变的情况下,ONNXRuntime GPU版一般都要比CPU快的。该问题已经提了相关issue(issue #13198)。推荐CPU端推理用rapidocr_onnxruntime或者rapidocr_openvino,GPU端用rapidocr_paddle
Q: 请问这个能在32位C#中用嘛? linkA: C#可以32位,要用32位的dll,但nuget上的onnxruntime不支持win7。
Q: Windows系统下,装完环境之后,运行示例程序之后,报错OSError: [WinError 126] 找不到指定的模組 linkA: 原因是Shapely库没有正确安装,如果是在Windows,可以在Shapely whl下载对应的whl包,离线安装即可;另外一种解决办法是用conda安装也可。
Q: Linux部署python的程序时,import cv2时会报ImportError: ligGL.so.1: cannot open shared object file: No such file or directory? linkA: 解决方法 有两个(来自群友ddeef):
Expand Down
6 changes: 3 additions & 3 deletions docs/inference_engine/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/onnxruntime/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/onnxruntime/infer_optim/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/onnxruntime/onnxruntime-gpu/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/openvino/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/openvino/infer-gpu/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/inference_engine/openvino/infer/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/index.html

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion docs/install_usage/index.xml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
安装 link 根据自己需求,先安装PaddlePaddle框架(CPU/GPU),并验证,参见: 官方教程,注意验证是否安装成功: import paddle print(paddle.utils.run_check()) # 如果出现PaddlePaddle is installed successfully!,说明您已成功安装。 安装rapidocr_paddle pip install rapidocr_paddle 使用 link CPU端推理 GPU端推理 前提是安装了CPU版的PaddlePaddle
import cv2 from rapidocr_paddle import RapidOCR engine = RapidOCR() image_path = &amp;#34;tests/test_files/ch_en_num.jpg&amp;#34; result, elapse_list = engine(image_path) print(result) print(elapse_list) 前提是安装了GPU版的PaddlePaddle,注意在实例化RapidOCR类时,需要通过参数显式指定使用GPU。
import cv2 from rapidocr_paddle import RapidOCR # 注意这里的参数 engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True) image_path = &amp;#34;tests/test_files/ch_en_num.jpg&amp;#34; result, elapse_list = engine(image_path) 其他使用详情,同rapidocor_onnxruntime系列,参见: link
推理速度比较 link 相关测评代码,参见AI Studio,Fork可直接运行查看。不要只推理一张来推理速度,推理第一张时,需要预热。</description>
推理速度比较 link 相关测评代码,参见AI Studio,Fork可直接运行查看。不要只推理一张来测试推理速度,需要先推理一张作为预热,后续再看推理速度。</description>
</item>

<item>
Expand Down
30 changes: 15 additions & 15 deletions docs/install_usage/rapidocr/cli/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr/install/index.html

Large diffs are not rendered by default.

78 changes: 39 additions & 39 deletions docs/install_usage/rapidocr/usage/index.html

Large diffs are not rendered by default.

18 changes: 9 additions & 9 deletions docs/install_usage/rapidocr_api/index.html

Large diffs are not rendered by default.

38 changes: 19 additions & 19 deletions docs/install_usage/rapidocr_paddle/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/desktop_usage/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/nuitka_package/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/ocrweb_multi/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/pyinstaller/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/install_usage/rapidocr_web/rapidocr_web/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/online_demo/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/other_programing_lan/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/overview/index.html

Large diffs are not rendered by default.

18 changes: 9 additions & 9 deletions docs/quickstart/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/related_projects/derivatives_projects/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/related_projects/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/related_projects/related_projects/index.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions docs/sponsor/index.html

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions index.xml
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@
安装 link 根据自己需求,先安装PaddlePaddle框架(CPU/GPU),并验证,参见: 官方教程,注意验证是否安装成功: import paddle print(paddle.utils.run_check()) # 如果出现PaddlePaddle is installed successfully!,说明您已成功安装。 安装rapidocr_paddle pip install rapidocr_paddle 使用 link CPU端推理 GPU端推理 前提是安装了CPU版的PaddlePaddle
import cv2 from rapidocr_paddle import RapidOCR engine = RapidOCR() image_path = &amp;#34;tests/test_files/ch_en_num.jpg&amp;#34; result, elapse_list = engine(image_path) print(result) print(elapse_list) 前提是安装了GPU版的PaddlePaddle,注意在实例化RapidOCR类时,需要通过参数显式指定使用GPU。
import cv2 from rapidocr_paddle import RapidOCR # 注意这里的参数 engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True) image_path = &amp;#34;tests/test_files/ch_en_num.jpg&amp;#34; result, elapse_list = engine(image_path) 其他使用详情,同rapidocor_onnxruntime系列,参见: link
推理速度比较 link 相关测评代码,参见AI Studio,Fork可直接运行查看。不要只推理一张来推理速度,推理第一张时,需要预热。</description>
推理速度比较 link 相关测评代码,参见AI Studio,Fork可直接运行查看。不要只推理一张来测试推理速度,需要先推理一张作为预热,后续再看推理速度。</description>
</item>

<item>
Expand Down Expand Up @@ -288,7 +288,7 @@ CDLA:中文文档版面分析数据集,面向中文文献类(论文)场
<pubDate>Sun, 02 Oct 2022 00:00:00 +0000</pubDate>

<guid>https://rapidai.github.io/RapidOCRDocs/docs/faq/</guid>
<description>Q: 为什么我的模型在GPU上比在CPU上还要慢? linkA: : 取决于所使用的执行提供者,它可能没有完全支持模型中的所有操作。回落到CPU操作可能会导致性能速度的下降。此外,即使一个操作是由CUDA execution provider实现的,由于性能的原因,它也不一定会把操作分配/放置到CUDA EP上。要想看到ORT决定的位置,请打开verbose日志并查看控制台的输出
<description>Q: 为什么我的模型在ONNXRuntime GPU版上比在CPU上还要慢? linkA: : 因为OCR任务中输入图像Shape是动态的。每次GPU上都需要重新清空上一次不同Shape的缓存结果。如果输入图像Shape不变的情况下,ONNXRuntime GPU版一般都要比CPU快的。该问题已经提了相关issue(issue #13198)。推荐CPU端推理用rapidocr_onnxruntime或者rapidocr_openvino,GPU端用rapidocr_paddle
Q: 请问这个能在32位C#中用嘛? linkA: C#可以32位,要用32位的dll,但nuget上的onnxruntime不支持win7。
Q: Windows系统下,装完环境之后,运行示例程序之后,报错OSError: [WinError 126] 找不到指定的模組 linkA: 原因是Shapely库没有正确安装,如果是在Windows,可以在Shapely whl下载对应的whl包,离线安装即可;另外一种解决办法是用conda安装也可。
Q: Linux部署python的程序时,import cv2时会报ImportError: ligGL.so.1: cannot open shared object file: No such file or directory? linkA: 解决方法 有两个(来自群友ddeef):
Expand Down
6 changes: 3 additions & 3 deletions sitemap.xml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
<lastmod>2023-10-21T16:09:49+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/docs/install_usage/rapidocr_paddle/</loc>
<lastmod>2023-10-31T19:49:32+08:00</lastmod>
<lastmod>2024-01-30T09:33:04+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/docs/install_usage/rapidocr/install/</loc>
<lastmod>2023-10-26T08:21:22+08:00</lastmod>
Expand Down Expand Up @@ -102,7 +102,7 @@
<lastmod>2024-01-23T09:39:10+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/docs/faq/</loc>
<lastmod>2023-09-28T08:38:57+08:00</lastmod>
<lastmod>2024-01-30T09:33:04+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/docs/blog/</loc>
<lastmod>2023-09-28T08:38:57+08:00</lastmod>
Expand Down Expand Up @@ -147,7 +147,7 @@
<lastmod>2023-09-28T08:38:57+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/</loc>
<lastmod>2024-01-23T09:39:10+08:00</lastmod>
<lastmod>2024-01-30T09:33:04+08:00</lastmod>
</url><url>
<loc>https://rapidai.github.io/RapidOCRDocs/categories/</loc>
</url><url>
Expand Down

0 comments on commit 2878833

Please sign in to comment.