Hi there .
Im trying to use a project that requires libtorch CPU acids-ircam/nn_tilde
Im able to build the object but unfortunately , I get a bunch of errors and ultimately it does not work .
Ive tried both prebuilt binaries from Qengineering/PyTorch-Raspberry-Pi-64-OS
and GitHub - ljk53/pytorch-rpi: Share PyTorch binaries built for Raspberry Pi
without success .
I get a weird output and Im sure Im missing some important step.
Would love if someone knows more about the topic by looking at this debug output:
Exception raised from RAIIFile at ../caffe2/serialize/file_adapter.cc:21 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x84 (0x7fa5918074 in /home/pi/pytorch/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0xe4 (0x7fa58fbb38 in /home/pi/pytorch/torch/lib/libc10.so)
frame #2: caffe2::serialize::FileAdapter::RAIIFile::RAIIFile(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0x128 (0x7f989ba1a8 in /home/pi/pytorch/torch/lib/libtorch_cpu.so)
frame #3: caffe2::serialize::FileAdapter::FileAdapter(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0x34 (0x7f989ba224 in /home/pi/pytorch/torch/lib/libtorch_cpu.so)
frame #4: torch::jit::load(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, c10::optional<c10::Device>, std::unordered_map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::hash<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::equal_to<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > >&) + 0x34 (0x7f99580f14 in /home/pi/pytorch/torch/lib/libtorch_cpu.so)
frame #5: torch::jit::load(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, c10::optional<c10::Device>) + 0x54 (0x7f99581074 in /home/pi/pytorch/torch/lib/libtorch_cpu.so)
frame #6: Backend::load(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x28 (0x7fa5961b4c in /home/pi/Documents/Pd/externals/nn~.pd_linux)
frame #7: nn_tilde_new(_symbol*, int, _atom*) + 0x100 (0x7fa5960764 in /home/pi/Documents/Pd/externals/nn~.pd_linux)
frame #8: pd_typedmess + 0x480 (0x556e21b4f8 in pd)
frame #9: new_anything + 0xa0 (0x556e21b698 in pd)
frame #10: binbuf_eval + 0xa10 (0x556e218588 in pd)
frame #11: <unknown function> + 0x8ecc0 (0x556e1fecc0 in pd)
frame #12: canvas_obj + 0x74 (0x556e2005cc in pd)
frame #13: binbuf_eval + 0xa10 (0x556e218588 in pd)
frame #14: binbuf_evalfile + 0x16c (0x556e218f54 in pd)
frame #15: glob_open + 0x60 (0x556e1c4950 in pd)
frame #16: pd_typedmess + 0x4fc (0x556e21b574 in pd)
frame #17: binbuf_eval + 0xa10 (0x556e218588 in pd)
frame #18: socketreceiver_read + 0x14c (0x556e227ec4 in pd)
frame #19: <unknown function> + 0xb6e74 (0x556e226e74 in pd)
frame #20: sys_pollgui + 0x14 (0x556e228b8c in pd)
frame #21: m_mainloop + 0x334 (0x556e220b0c in pd)
frame #22: __libc_start_main + 0xe8 (0x7fa6889218 in /lib/aarch64-linux-gnu/libc.so.6)
frame #23: <unknown function> + 0x18a28 (0x556e188a28 in pd)
Its basically a puredata object for audio as you can see in the repo .
In ubuntu PC works well , but on the pi I get this output.
I felt hope finding this instructions but unfortunately , something is off since there is no setup.py on the provided gdrive , then python3 setup.py clean cant be run