TensorFlow

type access

  • Operating System:

  • Terminal:

  • Shell:

  • Editor:

  • Package Manager:

  • Programming Language:

  • Utility:

  • NVIDIA Libraries:

type access

  • Operating System:

  • Terminal:

  • Shell:

  • Editor:

  • Package Manager:

  • Programming Language:

  • Utility:

  • NVIDIA Libraries:

type access

  • Operating System:

  • Terminal:

  • Shell:

  • Editor:

  • Package Manager:

  • Programming Language:

  • Utility:

  • NVIDIA Libraries:

type access

  • Operating System:

  • Terminal:

  • Shell:

  • Editor:

  • Package Manager:

  • Programming Language:

  • Utility:

  • NVIDIA Libraries:

type access

  • Operating System:

  • Terminal:

  • Shell:

  • Editor:

  • Package Manager:

  • Programming Language:

  • Utility:

  • NVIDIA Libraries:

TensorFlow is an open-source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture lets you deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code.

For basic usage of the Notebook environment, check the Jupyter Lab application.

For basic usage of the console environment, check the Terminal application.

Dependencies

For information on how to use the Dependencies parameter, please refer to the Initialization - Bash script and Initialization - pip packages section of the documentation.

Batch mode

Use this option to submit a Bash script (*.sh), which will be executed after the job starts. The job will stop after the execution of the program.

Start a terminal session

Instead of the default Jupyter Notebook, the user can start a terminal browser via the Terminal Interface parameter.

Run on GPU nodes

GPU partitions can be selected from the application frontend page using the Machine type parameter.

The NVIDIA System Management Interface program, nvidia-smi, can be used to monitor the usage of the GPU resources:

$ watch -n 0.5 nvidia-smi