fatih akyon

Evet şu anda torch SAHI’de zorunlu dependency. device olayı için şöyle bir şey yapabiliriz: DetectionModel için set_device diye bir fonksiyon tanımlayıp şu anki device set etme satırını ona taşırız. tensofflubhubdetectionmodel...

Güzel olmuş eline sağlık, try except’e gerek olmayabilir. torch’ta yaptığımız gibi try except yapmadan set edebiliriz gpu/cpu

Hello @tulasiram58827, thanks a lot for the work. Are you going to also add the onnx conversion for refine_net?

@DeepakSinghRawat @dogterbox @arj7192 There is already a packaged version that can be installed directly from pip: [pypi](https://pypi.org/project/craft-text-detector/) [github](https://github.com/fcakyon/craft-text-detector)

@bwheelz36 all you need is a PyPI token with publishing rights. Then PyPI publish can be automated by [a Github actions workflow](https://github.com/devrimcavusoglu/pybboxes/blob/main/.github/workflows/publish_pypi.yml) with no action required from the original owner...

So currently there is no way of contacting to PYPI owner in any way? Even if for only getting a token? If that's the case, then requesting from pypi-team is...

@AnilMandliya @djjandXMU i have fixed this issue in my fork: https://github.com/fcakyon/segan

@woshiZS unfortunately I no longer work on this project, I hope someone else can help you 👍

I have updated this repo for tensorflow>1.0 and python>3.5: https://github.com/fcakyon/segan @ghost @linan2 @YeBobr @lifelongeek @Qoboty

@SBrandeis I am having the same error when trying to upload a folder of files with a total size of 350MB. What is the proposed approach for such case?