Running TAO via Python Wheels

You can run TAO on a bare-metal system without Docker or K8s by using Python wheels that contain standalone implementations of the DNN functionality, pre-built and packaged into TAO containers.

This table maps each TAO wheel to its container and captures any exceptions associated with these wheels.

Wheel Name	Container Mapping	Networks Supported
nvidia-tao-pytorch	nvcr.io/nvidia/tao/tao-toolkit:6.0.0-pytorch	* action_recognition * centerpose * classification_pyt * deformable_detr * dino * grounding_dino * mask_grounding_dino * mask2former * mal * mae * ml_recog * nvdinov2 * ocdnet * ocrnet * optical_inspection * pointpillars * pose_classification * re_identification * rtdetr * segformer * stylegan_xl * visual_changenet
nvidia-tao-deploy	nvcr.io/nvidia/tao/tao-toolkit:6.0.0-deploy	* centerpose * classification_pyt * classification_tf1 * classification_tf2 * deformable_detr * detectnet_v2 * dino * dssd * grounding_dino * efficientdet_tf1 * efficientdet_tf2 * faster_rcnn * lprnet * mae * mask_rcnn * mask2former * mask_grounding_dino * ml_recog * multitask_classification * nvdinov2 * ocdnet * ocrnet * optical_inspection * rtdetr * retinanet * segformer * ssd * trtexec * unet * yolo_v3 * yolo_v4 * yolo_v4_tiny

Installing nvidia_tao_deploy Locally

This section details how to install the nvidia_tao_deploy wheel locally.

1. Install the following Python pip dependencies:

   python3 -m pip install --upgrade pip
   python3 -m pip install Cython==0.29.36
   python3 -m pip install nvidia-ml-py
   python3 -m pip install nvidia-pyindex
   python3 -m pip install --upgrade setuptools
   python3 -m pip install pycuda==2020.1
   python3 -m pip install nvidia-eff-tao-encryption
   python3 -m pip install nvidia-eff
   python3 -m pip install cffi
   

2. Set up openMPI and mpi4py:

   sudo apt-get install libopenmpi-dev -y
   python3 -m pip install mpi4py
   

3. Install the nvidia_tao_deploy wheel:

   python3 -m pip install nvidia-tao-deploy
   

Installing nvidia_tao_pytorch Locally

The nvidia-tao-pytorch wheel has several third-party dependencies, which can be cumbersome to install. To build the installation, refer to the steps on the GitHub page for the setup_env_desktop.sh script: