ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • Meta
    NVIDIA L4T PyTorch
    Container
    Meta
    NVIDIA L4T PyTorch

    PyTorch is a GPU accelerated tensor computational framework with a Python front end. This container contains PyTorch and torchvision pre-installed in a Python 3 environment to get up & running quickly with PyTorch on Jetson.

  • LayerLabelCreated
    sha256:e22fa2433191a8f119d18f077f7bcc198058846d6bd18a9618b034e2f0ee4e7aRUN
    OPENCV_DEB=OpenCV-4.5.0-aarch64.tar.gz OPENCV_URL=https://nvidia.box.com/shared/static/2hssa5g3v28ozvo3tc3qwxmn78yerca9.gz PYTORCH_URL=https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl PYTORCH_WHL=torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl TORCHAUDIO_VERSION=v0.12.0 TORCHVISION_VERSION=v0.13.0 TORCH_CUDA_ARCH_LIST=5.3;6.2;7.2 pip3 install --no-cache-dir --verbose pycuda six
    		08/04/2022 8:21 PM UTC
    sha256:45ee05a2c7cfcee371be20898ae54cbad644c61a39ff7272bc70779e51cff959RUN
    OPENCV_DEB=OpenCV-4.5.0-aarch64.tar.gz OPENCV_URL=https://nvidia.box.com/shared/static/2hssa5g3v28ozvo3tc3qwxmn78yerca9.gz PYTORCH_URL=https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl PYTORCH_WHL=torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl TORCHAUDIO_VERSION=v0.12.0 TORCHVISION_VERSION=v0.13.0 TORCH_CUDA_ARCH_LIST=5.3;6.2;7.2 echo "$PATH" &&
  echo "$LD_LIBRARY_PATH"
    		08/04/2022 8:14 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64:
    		08/04/2022 8:14 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    PATH=/usr/local/cuda/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
    		08/04/2022 8:14 PM UTC
    sha256:304a59e34f051db98a9d9d81773a268917a65bcd5cc216f64976aa35ba4caeddRUN
    OPENCV_DEB=OpenCV-4.5.0-aarch64.tar.gz OPENCV_URL=https://nvidia.box.com/shared/static/2hssa5g3v28ozvo3tc3qwxmn78yerca9.gz PYTORCH_URL=https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl PYTORCH_WHL=torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl TORCHAUDIO_VERSION=v0.12.0 TORCHVISION_VERSION=v0.13.0 TORCH_CUDA_ARCH_LIST=5.3;6.2;7.2 cd /tmp &&
  ./opencv_install.sh ${OPENCV_URL} ${OPENCV_DEB}
    		08/04/2022 8:14 PM UTC
    sha256:3105c51439a7caab335fe5c2289b769fbf4349f24d173dde10ff7f5ffda906c8COPY
    file:738b23d3effc8e9ffc54a87257f6eadd655f97205a53b370e43cf91ac36a2748 in /tmp/opencv_install.sh
    		08/04/2022 8:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    OPENCV_DEB=OpenCV-4.5.0-aarch64.tar.gz
    		08/04/2022 8:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    OPENCV_URL=https://nvidia.box.com/shared/static/5v89u6g5rb62fpz4lh0rz531ajo2t5ef.gz
    		08/04/2022 8:13 PM UTC
    sha256:8503bab2b7c91fa24a7fc487c9ebbd66c077d19884953f9c4a7b4b1c15220070RUN
    PYTORCH_URL=https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl PYTORCH_WHL=torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl TORCHAUDIO_VERSION=v0.12.0 TORCHVISION_VERSION=v0.13.0 TORCH_CUDA_ARCH_LIST=5.3;6.2;7.2 git clone --recursive -b ${TORCHAUDIO_VERSION} https://github.com/pytorch/audio torchaudio &&
  cd torchaudio &&
  sed -i 's#  URL https://zlib.net/zlib-1.2.11.tar.gz#  URL https://zlib.net/zlib-1.2.12.tar.gz#g' third_party/zlib/CMakeLists.txt ||
  echo "failed to patch torchaudio/third_party/zlib/CMakeLists.txt" &&
  sed -i 's#  URL_HASH SHA256=c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1#  URL_HASH SHA256=91844808532e5ce316b3c010929493c0244f3d37593afd6de04f71821d5136d9#g' third_party/zlib/CMakeLists.txt ||
  echo "failed to patch torchaudio/third_party/zlib/CMakeLists.txt" &&
  BUILD_SOX=1 python3 setup.py install &&
  cd ../ &&
  rm -rf torchaudio
    		08/04/2022 8:13 PM UTC
    sha256:e66981cc96494c4e7590780bea5ce60b8f87e114b4045f1d05454f0f460f4f00RUN
    PYTORCH_URL=https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl PYTORCH_WHL=torch-1.13.0a0+340c4120.nv22.06-cp38-cp38-linux_aarch64.whl TORCHAUDIO_VERSION=v0.12.0 TORCHVISION_VERSION=v0.13.0 TORCH_CUDA_ARCH_LIST=5.3;6.2;7.2 pip3 install --no-cache-dir scikit-build &&
  pip3 install --no-cache-dir ninja &&
  pip3 install --no-cache-dir --verbose pysoundfile
    		08/04/2022 7:50 PM UTC