You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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:
Also you can see on the following picture that the GPU is not being used by the OcrExtractor module:
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.
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:
Also you can see on the following picture that the GPU is not being used by the OcrExtractor module:
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?The text was updated successfully, but these errors were encountered: