Skip to content

Commit 25da46e

Browse files
AmberC0209AmberC0209
authored
update docs (#2629)
1 parent 0c38711 commit 25da46e

File tree

5 files changed

+142
-13
lines changed

5 files changed

+142
-13
lines changed

‎docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ comments: true
1313
<table>
1414
<thead>
1515
<tr>
16-
<th>模型</th><th>Model Download Link</th>
16+
<th>模型</th><th>模型下载链接</th>
1717
<th>Top-1 Acc（%）</th>
1818
<th>GPU推理耗时（ms）</th>
1919
<th>CPU推理耗时 (ms)</th>
@@ -23,7 +23,7 @@ comments: true
2323
</thead>
2424
<tbody>
2525
<tr>
26-
<td>PP-LCNet_x1_0_doc_ori</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-LCNet_x1_0_doc_ori_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x1_0_doc_ori_pretrained.pdparams">Trained Model</a></td>
26+
<td>PP-LCNet_x1_0_doc_ori</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-LCNet_x1_0_doc_ori_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x1_0_doc_ori_pretrained.pdparams">训练模型</a></td>
2727
<td>99.06</td>
2828
<td>3.84845</td>
2929
<td>9.23735</td>

‎docs/support_list/model_list_npu.en.md‎

Lines changed: 12 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -360,38 +360,40 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
360360
</table>
361361
<b>Note: The above accuracy metrics refer to Top-1 Accuracy on the [ImageNet-1k](https://www.image-net.org/index.php) validation set.</b>
362362

363-
## [图像多标签分类模块](../module_usage/tutorials/cv_modules/image_multilabel_classification.md)
363+
## [Image Multi-label Classification Module](../module_usage/tutorials/cv_modules/image_multilabel_classification.en.md)
364364
<table>
365365
<thead>
366366
<tr>
367-
<th>模型名称</th>
368-
<th>mAP（%）</th>
369-
<th>模型存储大小</th>
367+
<th>Model Name</th>
368+
<th>mAP (%)</th>
369+
<th>Model Storage Size</th>
370370
<th>Model Download Link</th></tr>
371371
</thead>
372372
<tbody>
373373
<tr>
374374
<td>CLIP_vit_base_patch16_448_ML</td>
375375
<td>89.15</td>
376376
<td>325.6 M</td>
377-
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/CLIP_vit_base_patch16_448_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/CLIP_vit_base_patch16_448_ML_pretrained.pdparams">Trained Model</a></td></tr>
377+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/CLIP_vit_base_patch16_448_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/CLIP_vit_base_patch16_448_ML_pretrained.pdparams">Training Model</a></td></tr>
378378
<tr>
379379
<td>PP-HGNetV2-B0_ML</td>
380380
<td>80.98</td>
381381
<td>39.6 M</td>
382+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B0_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">Training Model</a></td>
382383
<tr>
383384
<td>PP-HGNetV2-B4_ML</td>
384385
<td>87.96</td>
385386
<td>88.5 M</td>
386-
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B4_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B4_ML_pretrained.pdparams">Trained Model</a></td></tr>
387+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B4_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B4_ML_pretrained.pdparams">Training Model</a></td></tr>
387388
<tr>
388389
<td>PP-HGNetV2-B6_ML</td>
389-
<td>91.25</td>
390+
<td>91.06</td>
390391
<td>286.5 M</td>
391-
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B6_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B6_ML_pretrained.pdparams">Trained Model</a></td></tr>
392-
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B0_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">Trained Model</a></td></tr></tbody>
392+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B6_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B6_ML_pretrained.pdparams">Training Model</a></td></tr>
393+
</tr></tbody>
393394
</table>
394-
<b>注：以上精度指标为 [COCO2017](https://cocodataset.org/#home) 的多标签分类任务mAP。</b>
395+
<b>Note: The above accuracy metrics are for the multi-label classification task mAP of [COCO2017](https://cocodataset.org/#home).</b>
396+
395397

396398
## Object Detection Module
397399
<table>

‎docs/support_list/model_list_npu.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -379,6 +379,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
379379
<td>PP-HGNetV2-B0_ML</td>
380380
<td>80.98</td>
381381
<td>39.6 M</td>
382+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B0_ML_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">训练模型</a></td>
382383
<tr>
383384
<td>PP-HGNetV2-B4_ML</td>
384385
<td>87.96</td>
@@ -389,7 +390,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
389390
<td>91.06</td>
390391
<td>286.5 M</td>
391392
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B6_ML_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B6_ML_pretrained.pdparams">训练模型</a></td></tr>
392-
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PP-HGNetV2-B0_ML_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">训练模型</a></td></tr></tbody>
393+
</tr></tbody>
393394
</table>
394395
<b>注：以上精度指标为 [COCO2017](https://cocodataset.org/#home) 的多标签分类任务mAP。</b>
395396

‎docs/support_list/pipelines_list.en.md‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -306,6 +306,69 @@ comments: true
306306
<tr>
307307
<td>Text Recognition</td>
308308
</tr>
309+
<tr>
310+
<td rowspan = 2>General Image Recognition</td>
311+
<td>Subject Detection</td>
312+
<td rowspan = 2>None</td>
313+
<td rowspan = 2>The general image recognition production line is designed to address open-domain target localization and recognition issues. It can effectively identify and differentiate various target objects in different environments and conditions, making it widely applicable in autonomous driving, intelligent security, medical image analysis, and industrial automation, among other fields.</td>
314+
<td rowspan = 2>
315+
<ul>
316+
<li>Automated Identity Verification</li>
317+
<li>Unmanned Retail</li>
318+
<li>Autonomous Driving</li>
319+
</ul>
320+
</td>
321+
</tr>
322+
<tr>
323+
<td>Image Features</td>
324+
</tr>
325+
<tr>
326+
<td rowspan = 2>Pedestrian Attribute Recognition</td>
327+
<td>Pedestrian Detection</td>
328+
<td rowspan = 2>None</td>
329+
<td rowspan = 2>Pedestrian attribute recognition is a key function in computer vision systems used to locate and tag specific features of pedestrians in images or videos, such as gender, age, clothing color, and style.</td>
330+
<td rowspan = 2>
331+
<ul>
332+
<li>Smart City</li>
333+
<li>Security Monitoring</li>
334+
</ul>
335+
</td>
336+
</tr>
337+
<tr>
338+
<td>Pedestrian Attribute Recognition</td>
339+
</tr>
340+
<tr>
341+
<td rowspan = 2>Vehicle Attribute Recognition</td>
342+
<td>Vehicle Detection</td>
343+
<td rowspan = 2>None</td>
344+
<td rowspan = 2>Vehicle attribute recognition is an important component of computer vision systems. Its main task is to locate and tag specific attributes of vehicles in images or videos, such as vehicle type, color, and license plate number. This task not only requires accurate detection of vehicles but also the recognition of detailed attribute information for each vehicle.</td>
345+
<td rowspan = 2>
346+
<ul>
347+
<li>Intelligent Parking</li>
348+
<li>Traffic Management</li>
349+
<li>Autonomous Driving</li>
350+
</ul>
351+
</td>
352+
</tr>
353+
<tr>
354+
<td>Vehicle Attribute Recognition</td>
355+
</tr>
356+
<tr>
357+
<td rowspan = 2>Face Recognition</td>
358+
<td>Face Detection</td>
359+
<td rowspan = 2>None</td>
360+
<td rowspan = 2>The facial recognition task is an important component of the computer vision field, aiming to realize automatic personal identity recognition through the analysis and comparison of facial features.</td>
361+
<td rowspan = 2>
362+
<ul>
363+
<li>Security Authentication</li>
364+
<li>Monitoring Systems</li>
365+
<li>Social Media</li>
366+
</ul>
367+
</td>
368+
</tr>
369+
<tr>
370+
<td>Face Features</td>
371+
</tr>
309372
</table>
310373

311374
## 2. Featured Pipelines

‎docs/support_list/pipelines_list.md‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -308,6 +308,69 @@ comments: true
308308
<td>文本识别</td>
309309
</tr>
310310
<tr>
311+
<tr>
312+
<td rowspan = 2>通用图像识别</td>
313+
<td>主体检测</td>
314+
<td rowspan = 2>暂无</td>
315+
<td rowspan = 2>通用图像识别产线旨在解决开放域目标定位及识别问题，通用图像识别产线能够在不同的环境和条件下有效识别和区分各种目标物体，从而广泛应用于自动驾驶、智能安防、医疗影像分析以及工业自动化等多个领域。</td>
316+
<td rowspan = 2>
317+
<ul>
318+
<li>自动化身份核验</li>
319+
<li>无人零售</li>
320+
<li>自动驾驶</li>
321+
</ul>
322+
</td>
323+
</tr>
324+
<tr>
325+
<td>图像特征</td>
326+
</tr>
327+
<tr>
328+
<td rowspan = 2>行人属性识别</td>
329+
<td>行人检测</td>
330+
<td rowspan = 2>暂无</td>
331+
<td rowspan = 2>行人属性识别是计算机视觉系统中的关键功能，用于在图像或视频中定位并标记行人的特定特征，如性别、年龄、衣物颜色和款式等。</td>
332+
<td rowspan = 2>
333+
<ul>
334+
<li>智慧城市</li>
335+
<li>安防监控</li>
336+
</ul>
337+
</td>
338+
</tr>
339+
<tr>
340+
<td>行人属性识别</td>
341+
</tr>
342+
<tr>
343+
<td rowspan = 2>车辆属性识别</td>
344+
<td>车辆检测</td>
345+
<td rowspan = 2>暂无</td>
346+
<td rowspan = 2>车辆属性识别是计算机视觉系统中的重要组成部分，其主要任务是在图像或视频中定位并标记出车辆的特定属性，如车辆类型、颜色、车牌号等。该任务不仅要求准确检测出车辆，还需识别每辆车的详细属性信息。</td>
347+
<td rowspan = 2>
348+
<ul>
349+
<li>智能停车</li>
350+
<li>交通管理</li>
351+
<li>自动驾驶</li>
352+
</ul>
353+
</td>
354+
</tr>
355+
<tr>
356+
<td>车辆属性识别</td>
357+
</tr>
358+
<tr>
359+
<td rowspan = 2>人脸识别</td>
360+
<td>人脸检测</td>
361+
<td rowspan = 2>暂无</td>
362+
<td rowspan = 2>人脸识别任务是计算机视觉领域的重要组成部分，旨在通过分析和比较人脸特征，实现对个人身份的自动识别。</td>
363+
<td rowspan = 2>
364+
<ul>
365+
<li>安全认证</li>
366+
<li>监控系统</li>
367+
<li>社交媒体</li>
368+
</ul>
369+
</td>
370+
</tr>
371+
<tr>
372+
<td>人脸特征</td>
373+
</tr>
311374
</table>
312375

313376

0 commit comments

Comments
 (0)