asa008

Hi, @IvyGongoogle , @rainLiuplus , @JingzheLyp I have met the same problem, it seems that code length has changed, where should I add the code 'if mean is None: mean...

I encountered almost the same question, have you solved it? if so, how? @nsjiow thanks very much

you can try load model directly into GPU, like: ``` std::shared_ptr module = torch::jit::load(argv[1], torch::kCUDA); ```

F1030 16:15:43.990840 1937 math_functions.cu:28] Check failed: status == CUBLAS_STATUS_SUCCESS (13 vs. 0) CUBLAS_STATUS_EXECUTION_FAILED The above error will occur when installing CUDA9.0 By installing [patchesPatch 2](https://developer.nvidia.com/cuda-90-download-archive?target_os=Windows&target_arch=x86_64&target_version=10&target_type=exelocal) (Released Mar 5, 2018)solve