MyungJoo Ham

> I've added a basic runTest.sh to be able to invoke the tensorrt tensor_filter, but the test doesn't do any validation. Do you have a suggestion/pointer on how this test...

> > If this file is built with ANDROID=no && QNN_DELEGATE=yes, does QNN delegation work? or it does not? > > If it does not, we need explicit error at...

> @myungjoo In `filter_snpe.cc` there is same code for only-android-init. If the target is prepared properly, qnn delegate should work like Tizen-snpe. Ok. Now, my concerns are resolved. Thanks

I do not have a plan to provide timestamp for filters becauase I didn't even know that it is needed. Anyway, GSTBUF has timestamp information; thus, we will need to...

@DonghakPark Don't you need to do ```diff - platform_id_ = platform_id_; + this->platform_id_ = platform_id_; ```

Recommentation: Keep a PR with every related commits as a test basis and mark it "Do Not Merge" or "Draft PR" Make a number of independent smaller PRs ("sub-PR of...

Yes, as long as the pytorch installed in your machine, linked to nnstreamer, supports NVidia GPU, you can enforce using GPU by adding a property to tensor_filter, ```accelerator=true:gpu```. Check the...

The error message says what's wrong: ```CRITICAL : 16:43:59.669: Exception while loading the model: PyTorch is not linked with support for cuda devices``` Your pytorch is not built for CUDA....

> Thanks for your response! > > I have installed **pytorch 1.11.0 cuda version** on my Jetson AGX orin. I have checked the torch.cuda.is_available() and it gives true. But I...

You may build nnstreamer-pytorch (```/ext/nnstreamer/tensor_filter/tensor_filter_pytorch.cc```) with Pytorch 1.x in your machine. Then, extract and install the libnnstreamer_pytorch.so, or, build and install the whole nnstreamer with pytorch 1.x in your machine.