cmathx
cmathx
You can focus on mmap function in the resp. A little case costs much time is because mmap call method.
how to fix memory leak problem? I updated paddleocr to newest version (2.8.0). It also have this problem.
> the problem might be occurring because of the aggressive gradient clipping, therefore i tried different hyperparameters till the loss was stable,lower number of attention heads,attention dimensions and also a...
> > > the problem might be occurring because of the aggressive gradient clipping, therefore i tried different hyperparameters till the loss was stable,lower number of attention heads,attention dimensions and...
> > > the problem might be occurring because of the aggressive gradient clipping, therefore i tried different hyperparameters till the loss was stable,lower number of attention heads,attention dimensions and...
各位大佬，内存泄漏问题，后来怎么解决的啊？
> @cmathx The issue is not yet fully resolved. But you can try using Onnx models which are better than the default. to use onnx, it's too slow. With paddleocr...
It's cool. With my several ocr test on paddle/openvino/onnx model, using paddle model it's most quick. As memory leak is well fixed(I will test your mentioned suggestion), paddle model will...