search

NielsRogge / Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.
MIT License
8.51k stars 1.34k forks source link

Memory getting piled up while infering for table detection or table structure detection #273

Open Srivishnu27feb opened 1 year ago

Srivishnu27feb commented 1 year ago

Hi Team, I have a pdf of 20 pages and I am using pdf2image library to convert to images and passing each image for detection using threads and I could see the memory gets piles up and is not getting deallocated unless the entire application is exited... I tried debugging the code just when using table detection or table structure det the memory gets piledup.. in my flask application i am loading the model once and reusing in my function for infering each pages of pdf and also tried gc.collect() and del the variables but no luck... Is there any work around that could help in release the memory?

NielsRogge commented 1 year ago

Are you using the with torch.no_grad() context manager (as gradients are not needed at inference time)?

Srivishnu27feb commented 1 year ago

@NielsRogge yes I am using it with context manager.. I have a pdf document with 70 pages so I am using pdf2image conversion and passing it to the model for infer in my gpu machine.