-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
- Loading branch information
There are no files selected for viewing
Large diffs are not rendered by default.
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
<?xml version="1.0" encoding="utf-8" standalone="yes"?> | ||
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"> | ||
<channel> | ||
<title>模型相关 on RapidOCR Documentation</title> | ||
<link>https://rapidai.github.io/RapidOCRDocs/docs/about_model/</link> | ||
<description>Recent content in 模型相关 on RapidOCR Documentation</description> | ||
<generator>Hugo -- gohugo.io</generator> | ||
<language>en-us</language> | ||
<lastBuildDate>Tue, 22 Nov 2022 12:36:15 +0000</lastBuildDate><atom:link href="https://rapidai.github.io/RapidOCRDocs/docs/about_model/index.xml" rel="self" type="application/rss+xml" /> | ||
<item> | ||
<title>不同版本模型之间比较</title> | ||
<link>https://rapidai.github.io/RapidOCRDocs/docs/about_model/model_summary/</link> | ||
<pubDate>Mon, 11 Sep 2023 00:00:00 +0000</pubDate> | ||
|
||
<guid>https://rapidai.github.io/RapidOCRDocs/docs/about_model/model_summary/</guid> | ||
<description>各个版本ONNX模型效果对比(仅供参考) link⚠️注意: 以下测试结果均在自己构建测试集上评测所得,不代表在其他测试集上结果也是如此。 | ||
文本检测模型 link 评测采用的是TextDetMetric库 + 文本检测测试集,详情可以移步AI Studio运行查看。 | ||
⚠️注意:以下表格中推理时间是基于MacBook Pro M1运行所得,不同机器会有差别,请侧重查看彼此之间的比较。 | ||
指标计算都是在以下参数下计算得来,差别仅在于模型文件不同。 | ||
pre_process: DetResizeForTest: limit_side_len: 736 limit_type: min NormalizeImage: std: [0.229, 0.224, 0.225] mean: [0.485, 0.456, 0.406] scale: 1./255. order: hwc ToCHWImage: KeepKeys: keep_keys: [&#39;image&#39;, &#39;shape&#39;] post_process: thresh: 0.3 box_thresh: 0.5 max_candidates: 1000 unclip_ratio: 1.6 use_dilation: true score_mode: &#34;fast&#34; 模型 模型大小 Precision Recall H-mean Speed(s/img) ch_PP-OCRv4_det_infer.onnx 4.5M 0.6958 0.8608 0.7696 0.6176 ch_PP-OCRv4_det_server_infer.onnx 108M 0.7070 0.9330 0.8044 13.9348 ch_PP-OCRv3_det_infer.onnx 2.3M 0.</description> | ||
</item> | ||
|
||
<item> | ||
<title>支持识别语言及自助转换模型</title> | ||
<link>https://rapidai.github.io/RapidOCRDocs/docs/about_model/support_language/</link> | ||
<pubDate>Mon, 11 Sep 2023 00:00:00 +0000</pubDate> | ||
|
||
<guid>https://rapidai.github.io/RapidOCRDocs/docs/about_model/support_language/</guid> | ||
<description>支持识别的语言 link 因为本项目依托于PaddleOCR,所以理论上PaddleOCR支持识别的模型,RapidOCR都是支持的。 中英文检测和识别(可以直接使用) link 因为中英文是最为常用的模型,所以在打包时,就默认将中英文识别的模型放到了rapidocr_onnxruntime和rapidocr_openvino中,直接pip安装即可使用。 其他语种检测和识别(需要转换) link PaddleOCR中已有文本检测模型列表:link PaddleOCR已有文本识别模型列表: link 除了slim和蒸馏过的模型,上面链接中的其他模型都可以转换为ONNX格式,通过RapidOCR快速部署。 自助转换使用教程 link ⚠️ 主要借助paddleocr_convert库来实现。 在线快速转换 link 通过Hugging Face上的应用,快速转换模型。整体界面是下面这个样子 离线安装库转换 link 安装paddleocr_convert pip install paddleocr_convert 命令行使用 用法: $ paddleocr_convert -h usage: paddleocr_convert [-h] [-p MODEL_PATH] [-o SAVE_DIR] [-txt_path TXT_PATH] optional arguments: -h, --help show this help message and exit -p MODEL_PATH, --model_path MODEL_PATH The inference model url or local path of paddleocr. e.g. https://paddleocr.bj.bcebos.com/PP- OCRv3/chinese/ch_PP-OCRv3_det_infer.tar or models/ch_PP-OCRv3_det_infer.tar -o SAVE_DIR, --save_dir SAVE_DIR The directory of saving the model.</description> | ||
</item> | ||
|
||
</channel> | ||
</rss> |
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.