【开源实习】越南语语种的多模态数据资源在昇腾AI开发板上运行应用 #136
Open
uMemory wants to merge 2 commits into
Open
Conversation
uMemory
changed the title
Contributor
|
代码文件中添加数据集和模型下载的代码实现 |
Contributor
|
辛苦代码合入master分支的orange-pi-mindspore/Online/community目录下，项目目录和代码文件命名格式参考代码仓中已有项目的格式；同时目录orange-pi-mindspore/Online/，orange-pi-mindspore/Online/community/下的readme文件对应位置补充该项目的相关版本信息 |
Contributor
|
为了代码规范，默认设置已经是PYNATIVE_MODE，所以删除代码中的ms.set_context(mode=ms.PYNATIVE_MODE）部分 |
uMemory
force-pushed
the
feature/search_text_image_pair
branch
2 times, most recently
from
April 22, 2026 01:46
50e26ae to
323110e
Compare
… with relative links
uMemory
force-pushed
the
feature/search_text_image_pair
branch
from
April 22, 2026 02:20
f75dd2b to
838db50
Compare
Author
|
已按照要求修改了代码并更新了相关的README.md，调整PR合并至master分支 |
Contributor
|
验收通过，可以合入 |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description: 开源实习任务#2079
This PR implements a Vietnamese image-text semantic search application as part of the OpenDataLab "WanJuan-Silk Road" community task. The goal is to demonstrate multimodal data processing and retrieval on the OrangePi AIpro20T.
Approach: Uses the MindNLP framework with the XLM-RoBERTa model to generate embeddings for Vietnamese text and images, enabling semantic cross-modal retrieval.
Related Issue: Fixes #2079 (Ref: mindspore/community#2079).
Changes:
1.New Module:
Online/community/ImageTextPairSearching2.Core Files: Added mindspore_image_text_pair_searching.ipynb for the interactive search pipeline and a comprehensive README.md for deployment guidance.
Testing & Benchmark:
Environment: Verified on OrangePi AIpro20T with CANN 8.1.RC1, MindSpore 2.5.0, Python 3.9 and MindNLP 0.4.1.
Functionality: Successfully retrieved relevant images using Vietnamese queries with similarity scores verified in the demo output.
Checklist
Reviewers