Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Delete #304

Closed
ChesonHuang opened this issue Apr 22, 2024 · 0 comments
Closed

Delete #304

ChesonHuang opened this issue Apr 22, 2024 · 0 comments

Comments

@ChesonHuang
Copy link

ChesonHuang commented Apr 22, 2024

先占个坑(本周内填完),记录我实现应用的心得,以供需要的人参考。
为实现类似README中的应用,分为前后端的部署。

前端的部署

后端服务的部署

步骤1:数据的处理

clip-retrieval里案例处理数据集是用img2dataset, 除了这种方式,你还可以自己处理数据对,保证图文匹配就行。例如:你保证你的数据集文件夹下:有 xxxx.png和xxxx.txt即可,这个xxxx是个ID,同一个图片和文本对要保证一致。

步骤2:all_clip的改动

all_clip不支持chinese clip,需要手动添加支持,代码参考这里添加即可:data2ml/all-clip#27

步骤3:clip_retrieval代码优化

问题1: Can't pickle local object 'get_image_dataset..ImageDataset'
这是个多线程的问题,加上参数--num_prepro_workers=1即可
问题2: 当采用自己的图片文本对的时候,报错self.images not found key
这是bug, 参考这里的解决 办法

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant