Nvidia_tao_deploy installation on Xavier

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) Jetson Xavier
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) efficientdet-tf1

I have installed nvidia_tao_deploy successfully into Jetson Xavier directly.
All the following commands are successfully installed.

apt install libopenmpi-dev
pip install nvidia_tao_deploy==5.0.0.423.dev0
pip install https://files.pythonhosted.org/packages/f7/7a/ac2e37588fe552b49d8807215b7de224eef60a495391fdacc5fa13732d11/nvidia_eff_tao_encryption-0.1.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
pip install https://files.pythonhosted.org/packages/0d/05/6caf40aefc7ac44708b2dcd5403870181acc1ecdd93fa822370d10cc49f3/nvidia_eff-0.6.2-py38-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

After installation, I am going to do conversion on Xavier device for efficientdet-tf1 trained model into engine.

I have command not found error.

atic@ubuntu:~$ efficientdet_tf1 gen_trt_engine -h
bash: efficientdet_tf1: command not found

Why I cann’t do generating engine after successfully installation of nvidia_tao_deploy on Xavier?

The successful installation is found as follows.

atic@ubuntu:~$ pip3 install nvidia_tao_deploy==5.0.0.423.dev0
Requirement already satisfied: nvidia_tao_deploy==5.0.0.423.dev0 in ./.local/lib/python3.8/site-packages (5.0.0.423.dev0)
Requirement already satisfied: pynvml==11.0.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (11.0.0)
Requirement already satisfied: omegaconf==2.2.2 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (2.2.2)
Requirement already satisfied: pyclipper==1.1.0.post3 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.1.0.post3)
Requirement already satisfied: six>=1.12.0 in /usr/lib/python3/dist-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.14.0)
Requirement already satisfied: PyYAML>=5.1 in /usr/lib/python3/dist-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (5.3.1)
Requirement already satisfied: pycocotools in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (2.0.7)
Requirement already satisfied: requests>=2.31.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (2.31.0)
Requirement already satisfied: absl-py>=0.7.1 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (2.0.0)
Requirement already satisfied: seaborn==0.7.1 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (0.7.1)
Collecting protobuf==3.20.1
  Using cached protobuf-3.20.1-cp38-cp38-manylinux2014_aarch64.whl (918 kB)
Requirement already satisfied: scikit-image==0.17.2 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (0.17.2)
Requirement already satisfied: onnx in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.15.0)
Requirement already satisfied: Pillow<9.0.0,>=8.1.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (8.4.0)
Requirement already satisfied: hydra-core==1.2.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.2.0)
Requirement already satisfied: scipy==1.5.4 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.5.4)
Requirement already satisfied: matplotlib>=3.0.3 in /usr/lib/python3/dist-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (3.1.2)
Requirement already satisfied: mpi4py>=3.0.3 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (3.1.5)
Requirement already satisfied: scikit-learn==0.24.2 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (0.24.2)
Requirement already satisfied: natsort in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (8.4.0)
Requirement already satisfied: shapely==1.8.2 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.8.2)
Requirement already satisfied: numpy<=1.23.1 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.23.1)
Requirement already satisfied: opencv-python in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (4.8.1.78)
Requirement already satisfied: onnxruntime in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (1.16.1)
Requirement already satisfied: h5py==3.7.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (3.7.0)
Requirement already satisfied: tqdm==4.64.0 in ./.local/lib/python3.8/site-packages (from nvidia_tao_deploy==5.0.0.423.dev0) (4.64.0)
Requirement already satisfied: antlr4-python3-runtime==4.9.* in ./.local/lib/python3.8/site-packages (from omegaconf==2.2.2->nvidia_tao_deploy==5.0.0.423.dev0) (4.9.3)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/lib/python3/dist-packages (from requests>=2.31.0->nvidia_tao_deploy==5.0.0.423.dev0) (1.25.8)
Requirement already satisfied: charset-normalizer<4,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.31.0->nvidia_tao_deploy==5.0.0.423.dev0) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.31.0->nvidia_tao_deploy==5.0.0.423.dev0) (2.8)
Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.31.0->nvidia_tao_deploy==5.0.0.423.dev0) (2019.11.28)
Requirement already satisfied: PyWavelets>=1.1.1 in ./.local/lib/python3.8/site-packages (from scikit-image==0.17.2->nvidia_tao_deploy==5.0.0.423.dev0) (1.4.1)
Requirement already satisfied: networkx>=2.0 in ./.local/lib/python3.8/site-packages (from scikit-image==0.17.2->nvidia_tao_deploy==5.0.0.423.dev0) (3.1)
Requirement already satisfied: imageio>=2.3.0 in ./.local/lib/python3.8/site-packages (from scikit-image==0.17.2->nvidia_tao_deploy==5.0.0.423.dev0) (2.31.6)
Requirement already satisfied: tifffile>=2019.7.26 in ./.local/lib/python3.8/site-packages (from scikit-image==0.17.2->nvidia_tao_deploy==5.0.0.423.dev0) (2023.7.10)
Requirement already satisfied: importlib-resources; python_version < "3.9" in ./.local/lib/python3.8/site-packages (from hydra-core==1.2.0->nvidia_tao_deploy==5.0.0.423.dev0) (6.1.0)
Requirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from hydra-core==1.2.0->nvidia_tao_deploy==5.0.0.423.dev0) (23.2)
Requirement already satisfied: joblib>=0.11 in ./.local/lib/python3.8/site-packages (from scikit-learn==0.24.2->nvidia_tao_deploy==5.0.0.423.dev0) (1.3.2)
Requirement already satisfied: threadpoolctl>=2.0.0 in ./.local/lib/python3.8/site-packages (from scikit-learn==0.24.2->nvidia_tao_deploy==5.0.0.423.dev0) (3.2.0)
Requirement already satisfied: sympy in ./.local/lib/python3.8/site-packages (from onnxruntime->nvidia_tao_deploy==5.0.0.423.dev0) (1.12)
Requirement already satisfied: flatbuffers in ./.local/lib/python3.8/site-packages (from onnxruntime->nvidia_tao_deploy==5.0.0.423.dev0) (23.5.26)
Requirement already satisfied: coloredlogs in ./.local/lib/python3.8/site-packages (from onnxruntime->nvidia_tao_deploy==5.0.0.423.dev0) (15.0.1)
Requirement already satisfied: zipp>=3.1.0; python_version < "3.10" in ./.local/lib/python3.8/site-packages (from importlib-resources; python_version < "3.9"->hydra-core==1.2.0->nvidia_tao_deploy==5.0.0.423.dev0) (3.17.0)
Requirement already satisfied: mpmath>=0.19 in ./.local/lib/python3.8/site-packages (from sympy->onnxruntime->nvidia_tao_deploy==5.0.0.423.dev0) (1.3.0)
Requirement already satisfied: humanfriendly>=9.1 in ./.local/lib/python3.8/site-packages (from coloredlogs->onnxruntime->nvidia_tao_deploy==5.0.0.423.dev0) (10.0)
ERROR: onnx 1.15.0 has requirement protobuf>=3.20.2, but you'll have protobuf 3.20.1 which is incompatible.
Installing collected packages: protobuf
  Attempting uninstall: protobuf
    Found existing installation: protobuf 3.20.2
    Uninstalling protobuf-3.20.2:
      Successfully uninstalled protobuf-3.20.2
Successfully installed protobuf-3.20.1
2

Refer to “Running TAO Deploy on Jetson devices” section in GitHub - NVIDIA/tao_deploy: Package for deploying deep learning models from TAO Toolkit, it is expected to install something inside a docker.
For example,

$ docker run --runtime=nvidia -it --rm  nvcr.io/nvidia/l4t-tensorrt:r8.5.2.2-devel /bin/bash
3

I am not using docker. Since I have tensorrt installed in my Xavier, nvidia_tao_deploy is directly installed into system, not to docker.

atic@ubuntu:/opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/Rectitude$ dpkg -l | grep nvinfer
ii  libnvinfer-bin                             8.5.2-1+cuda11.4                     arm64        TensorRT binaries
ii  libnvinfer-dev                             8.5.2-1+cuda11.4                     arm64        TensorRT development libraries and headers
ii  libnvinfer-plugin-dev                      8.5.2-1+cuda11.4                     arm64        TensorRT plugin libraries
ii  libnvinfer-plugin8                         8.5.2-1+cuda11.4                     arm64        TensorRT plugin libraries
ii  libnvinfer-samples                         8.5.2-1+cuda11.4                     all          TensorRT samples
ii  libnvinfer8                                8.5.2-1+cuda11.4                     arm64        TensorRT runtime libraries
ii  python3-libnvinfer                         8.5.2-1+cuda11.4                     arm64        Python 3 bindings for TensorRT
ii  python3-libnvinfer-dev                     8.5.2-1+cuda11.4                     arm64        Python 3 development package for TensorRT
4

Could you search “efficientdet_tf1” to check where is it?

5

Nothing comes out.

atic@ubuntu:/opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/Rectitude$ which efficientdet_tf1
atic@ubuntu:/opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/Rectitude$
6

Please try:
$ sudo find / -name efficientdet_tf1

7 
atic@ubuntu:/opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/Rectitude$ sudo find / -name efficientdet_tf1
[sudo] password for atic: 
find: ‘/proc/9493’: No such file or directory
/home/atic/.local/bin/efficientdet_tf1
/home/atic/.local/lib/python3.8/site-packages/nvidia_tao_deploy/cv/efficientdet_tf1
find: ‘/run/user/1000/doc’: Permission denied
find: ‘/run/user/1000/gvfs’: Permission denied
find: ‘/run/user/124/gvfs’: Permission denied

Thanks it works now.

8

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.