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

OcrExtractor consuming a lot of RAM and not using GPU #262

Open
davidcbbc opened this issue Mar 6, 2025 · 1 comment
Open

OcrExtractor consuming a lot of RAM and not using GPU #262

davidcbbc opened this issue Mar 6, 2025 · 1 comment
Labels
enhancement New feature or request

Comments

@davidcbbc
Copy link

Hey!

After using AIL for a while I noticed that the OcrExtractor module that uses easyocr is consuming a lot of ram. Therefore, I updated my AIL machine with a GPU and restarted the AIL process. Nonetheless, it seems the module is not using the GPU by default and still consuming a lot of RAM , as seen in the next picture:

Image

Also you can see on the following picture that the GPU is not being used by the OcrExtractor module:

Image

After searching a little I've found this link where it states that the easyocr Reader function in https://github.com/ail-project/ail-framework/blob/master/bin/lib/objects/Ocrs.py should be called with gpu=True to use the GPU accelaration - any thoughts?

@adulau
Copy link
Member

adulau commented Mar 6, 2025

That's indeed correct. You need to add the gpu=True when instantiating easyOCR. We might need indeed to add it as a configuration parameter for the next release to make it more easy to enable.

@adulau adulau added the enhancement New feature or request label Mar 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants