docs: add Dragon Q6A NPU dev zh-dos#921
Merged
Merged
Conversation
![windsurf-bot[bot]](https://avatars.githubusercontent.com/in/1066231?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Other comments (16)
-
docs/common/ai/_inception_v3_qai-app-builder-6490.mdx (7-7)
The tip component is not properly closed. Please add a closing `:::` tag after the link.
请根据 [**QAI AppBuilder 安装方法**](qai-appbuilder) ::: - docs/common/ai/_qairt-quick-example.mdx (53-53) The paths in the validation script don't seem to match the directory structure from the running example. After changing to `resnet50_qairt/6490` directory, the paths like `../model/test_list.txt` may not be correct. Please verify the correct paths for the validation script.
- docs/common/ai/_qairt-sdk.mdx (87-87) This link appears to be self-referential. Since this file is '_qairt-sdk.mdx', linking to 'qairt-sdk#qairt' may create a circular reference. Consider linking directly to the specific section or using a different reference.
- docs/common/ai/_qairt-install.mdx (133-143) The AI framework installation section lists the frameworks and versions but doesn't provide actual installation commands. Consider adding installation instructions for these frameworks to maintain consistency with the detailed approach in other sections.
-
docs/common/ai/_qairt-model-zoo.mdx (2-2)
The links to QAIRT and QAI-APPBUILDER might be broken. Consider using full paths or relative paths to ensure they work correctly.
用户可以直接下载然后使用 [QAIRT](/common/ai/qairt-sdk#qairt) 或者 [QAI-APPBUILDER](/common/ai/qai-appbuilder) 进行部署 - docs/common/ai/_qai-appbuilder.mdx (48-48) The tip message about virtual environment is incomplete. It should be '安装 python 库前需要创建虚拟环境进行环境隔离' instead of '安装 python 库前需要创建虚拟环境进行环境隔'.
- docs/common/ai/_qairt-install.mdx (45-45) The tip block closing tag `:::` has incorrect indentation which might cause rendering issues. It should be aligned with the opening tag.
-
docs/common/ai/_qairt-quick-example.mdx (8-9)
The bash code block for the download example is incorrectly formatted. The commands should be on separate lines:
```bash pip3 install modelscope modelscope download --model radxa/resnet50_qairt --local ./resnet50_qairt</li> <li> <a href="https://github.com/radxa-docs/docs/pull/921/files#diff-0283969cc00962ad4f7a86c41c82255ab0511d710ca022cc11b6ed761f26b518R67">docs/common/ai/_qairt-quick-example.mdx (67-67)</a> There appears to be a typo in the Chinese text: '类容' should probably be '内容' (content). </li> <li> <a href="https://github.com/radxa-docs/docs/pull/921/files#diff-f46622209df9c244ca995272d1ba932fdf71adc01a7c553dad3f3b9868146219R8">docs/common/ai/_qairt-usage.mdx (8-8)</a> The image width style property is missing a unit. Consider adding a percentage or pixel unit: ```suggestion <img src="/img/dragon/q6a/qairt_workflow.webp" style={{ width: "65%" }} /> -
docs/common/ai/_qairt-usage.mdx (342-342)
There's a typo in this line - '例字' should probably be '例子' (example):
请根据 SoC NPU 架构选择相应的 hexagon 文件夹, 这里以 QCS6490 为例子 -
docs/common/ai/_qairt-usage.mdx (410-410)
There appears to be a typo in this line - '类容' should probably be '内容':
通过结果打印与测试图片内容对比，可以确认 resnet50 模型移植到 Qualcomm® NPU 上输出的结果正确。 -
docs/common/ai/_qairt-usage.mdx (226-226)
There's a typo in this line - 'DCL' should be 'DLC':
`graph_names`: 模型的图名称列表，与未量化的 DLC 模型文件名同名 （不带后缀） -
docs/common/ai/_qairt-usage.mdx (232-232)
There's a typo in this line - 'dsp_arc' should be 'dsp_arch' to match the parameter name in the JSON example:
`dsp_arch`: NPU 架构 - docs/common/ai/_qairt-install.mdx (127-127) The command for installing Python dependencies doesn't show its expected output, unlike the other commands in this document. Consider adding the expected output for consistency.
-
docs/common/ai/_qairt-usage.mdx (348-348)
There's a hardcoded IP address in this command. For consistency with other commands, consider using the placeholder:
scp ./* ubuntu@<ip address>:/home/ubuntu/resnet50_qairt_example/model
💡 To request another review, post a new comment with "/windsurf-review".
Comment on lines
+1
to
+2
| 此文档讲述如何使用 QAI AppBuilder python 库在瑞莎 Dragon Q6A 上运行 [GoogLeNet](https://aihub.qualcomm.com/models/googlenet?domain=Computer+Vision&useCase=Image+Classification&chipsets=qualcomm-qcs6490-proxy) | ||
| 目标识别模型。 |
Contributor
There was a problem hiding this comment.
There's an inconsistency in the document. The filename and content appear to be about Real-ESRGAN (super-resolution), but the first paragraph incorrectly mentions running GoogLeNet (image classification). Please update the introduction to correctly describe Real-ESRGAN instead of GoogLeNet.
Contributor
Author
There was a problem hiding this comment.
thanks, i would change
Comment on lines
+54
to
+55
| pip3 install venv | ||
| python3 -m venv .venv |
Contributor
There was a problem hiding this comment.
The command to install the venv package is incorrect. The Python venv module is built-in and doesn't need to be installed with pip. If it's not available, you should use apt install python3-venv on Debian/Ubuntu systems.
Suggested change
| pip3 install venv | |
| python3 -m venv .venv | |
| apt install python3-venv | |
| python3 -m venv .venv |
| 关于 AIMET 更多详细文档请参考 | ||
|
|
||
| - [**AIMET DOCS**](https://quic.github.io/aimet-pages/releases/latest/index.html#) | ||
| - [**AIMET 仓库**](<(https://github.com/quic/aimet)>) |
Contributor
There was a problem hiding this comment.
There's a syntax error in the AIMET repository link. The extra angle brackets will break the URL.
Suggested change
| - [**AIMET 仓库**](<(https://github.com/quic/aimet)>) | |
| - [**AIMET 仓库**](https://github.com/quic/aimet) |
signed-off-by: "Morgan ZHANG" <zifengzhang18@gmail.com>
nascs
approved these changes
Sep 8, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
docs: add Dragon Q6A NPU dev zh-dos