NVIDIA Jetson JetPack 5.0.1に PyTorchを NVIDIA公式の手順でインストールする方法

【2020年版】NVIDIA Jetson Nano、Jetson Xavier NXの便利スクリプト

# JetPack 5.0.2

$ uname -a
Linux ubuntu 5.10.104-tegra #1 SMP PREEMPT Wed Aug 10 20:17:07 PDT 2022 aarch64 aarch64 aarch64 GNU/Linux

$ /usr/local/cuda/bin/nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_May__4_00:02:26_PDT_2022
Cuda compilation tools, release 11.4, V11.4.239
Build cuda_11.4.r11.4/compiler.31294910_0

# Install system packages required by PyTorch
sudo apt-get -y update

sudo apt-get -y install autoconf bc build-essential g++-8 gcc-8 clang-8 lld-8 gettext-base gfortran-8 iputils-ping libbz2-dev libc++-dev libcgal-dev libffi-dev libfreetype6-dev libhdf5-dev libjpeg-dev liblzma-dev libncurses5-dev libncursesw5-dev libpng-dev libreadline-dev libssl-dev libsqlite3-dev libxml2-dev libxslt-dev locales moreutils openssl python-openssl rsync scons python3-pip libopenblas-dev;

# Install PyTorch
# https://developer.download.nvidia.com/compute/redist/jp/v502/pytorch/

python3 -m pip install --upgrade pip
# Successfully installed pip-22.3.1

# python3 -m pip install aiohttp numpy=='1.19.4' scipy=='1.5.3'
python3 -m pip install aiohttp numpy=='1.21.1' scipy=='1.5.4' protobuf=='3.19.6'

export "LD_LIBRARY_PATH=/usr/lib/llvm-8/lib:$LD_LIBRARY_PATH"
echo $LD_LIBRARY_PATH

# python3 -m pip install --upgrade protobuf

# NVIDIA Framework Container 22.11
export TORCH_INSTALL=https://developer.download.nvidia.com/compute/redist/jp/v502/pytorch/torch-1.13.0a0+936e9305.nv22.11-cp38-cp38-linux_aarch64.whl
python3 -m pip install --no-cache $TORCH_INSTALL
# Installing collected packages: torch
# Successfully installed torch-1.13.0a0+936e9305.nv22.11

# Check torch enabled CUDA

$ python3 -c "import torch; print(torch.cuda.is_available())"
True

$ python3 -c "import torch; print(torch.cuda.is_available())"
NvRmMemInitNvmap failed with Permission denied
549: Memory Manager Not supported

****NvRmMemInit failed**** error type: 196626

*** NvRmMemInit failed NvRmMemConstructor
/home/jetson/.local/lib/python3.8/site-packages/torch/cuda/__init__.py:83: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 801: operation not supported (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:109.)
  return torch._C._cuda_getDeviceCount() > 0
False

$ python3 -c "import torch; print(torch.cuda.is_available())"
False

AssertionError: Torch not compiled with CUDA enabled

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
whisper 1.0 requires torch, which is not installed.
tensorflow-cpu-aws 2.10.0 requires numpy>=1.20, but you have numpy 1.19.4 which is incompatible.
tensorflow-cpu-aws 2.10.0 requires protobuf<3.20,>=3.9.2, but you have protobuf 4.21.9 which is incompatible.
tensorboard 2.10.1 requires protobuf<3.20,>=3.9.2, but you have protobuf 4.21.9 which is incompatible.

NVIDIA Jetsonで音声認識の Whisperを動かす方法

NVIDIA Jetsonで流行の AIお絵かきの min(DALL・E)を動かす方法

NVIDIA Jetson JetPack 5.0.1に TensorFlowを NVIDIA公式の手順でインストールする方法