kminemur

@wallacezq probably the error comes from reshape (line 57-58), since openvino API2.0, the model shape changed. You may try net.reshape({net.inputs[0]: PartialShape( [self.EmbedBatchSize, 3, self.EmbedWindowLength, self.ImgSizeHeight, self.ImgSizeWidth])})

the models come from which openvino version? 2022.1?

I reproduced your issue. will take a look

Hi i3d-rgb-tf model was changed, so need to fix some part of codes. Workaround: please change segmentor.py as following **[L56-61]** net = core.read_model(i3d_path) net.reshape({net.inputs[0]: PartialShape( \ [self.EmbedBatchSize, self.EmbedWindowLength, self.ImgSizeHeight, self.ImgSizeWidth,...

Thanks for the comment will create patch

Hi @christinaburge May we know why you need this implementation, any background? To use your-defined bias data type in oneDNN. you can change bias memory primitives & memory descriptor in...

cmake out log is as follows: >cmake --version cmake version 3.29.5-msvc4 cmake .. -DZFP_WITH_CUDA=TRUE --log-level=VERBOSE -- Building for: Visual Studio 17 2022 -- Selecting Windows SDK version 10.0.22621.0 to target...

Hi, sorry for late response. CUDA code samples can be compiled without any issue on my env. zfp builds with CUDA disabled also can be build on my env. thank...

Not working, got linking error. e.g. error LNK2019: unresolved external symbol cudaGetLastError referenced in function "bool __cdecl cuZFP::is_gpu_ptr(void const *)" (?is_gpu_ptr@cuZFP@@YA_NPEBX@Z) Btw, I think you can check it on your...

I mean just compiling without NVIDA GPU.　Issue here is code generation. I will wait the fix then.