3togo

@ranftlr , I try to trace your "dpt_hybrid-midas-d889a10e.pt" using torch.jit.trace but failed Below is the error message: File "/usr/local/lib/python3.9/dist-packages/torch/_tensor.py", line 867, in unflatten return super(Tensor, self).unflatten(dim, sizes, names) RuntimeError: NYI:...

Thank you for efforts due to so many peoples. The problem is fixed by using the latest version of pytorch.

I got the following errors when I try to trace "dpt_beit_large_384.pt". Any help? ``` Traceback (most recent call last): File "/work/gitee/MiDaS-cpp/python/export_model.py", line 162, in convert(in_model_type, in_model_path, out_model_path) File "/work/gitee/MiDaS-cpp/python/export_model.py", line...

let model = tch::CModule::load_on_device(model_path, device).unwrap(); let model: Rc = Rc::new(&model); let model2 = model.clone(); Rc will only clone a pointer to the same allocation. My problem is that due to...

Below is extract from cloneable.h in "torch/csrc/api/include/nn/cloneable.h" But I don't know how to translate it to rust. ` /// Performs a recursive "deep copy" of the `Module`, such that all...

ubuntu 22.10 might be very different. gcc -o example example.c -llapacke => won't work gcc -o example example.c -llapack => could compile but with segmentation fault 0x00007fffee7a0193 in mkl_lapack.dggsvd3_ ()...

not working [HlsImProc.hpp.txt](https://github.com/kyk0910/HLS-canny-edge-detection/files/3219305/HlsImProc.hpp.txt)

setting CUDA_architecture_build_targets to less than 8.6 could avoid the problem. eg. -DCUDA_architecture_build_targets=7.5

> Can you try to delete the ~/.arrayfire folder and build again. You may have some stale kernels in that directory. deleting the folder ~/.arrayfire does not fix the problem...

> Hey @3togo, > > I think the issue is because you have multiple GPUs and the OpenGL context is created on the second GPU. Can you try to set...