Provision a GPU compute environment on Oracle Cloud Infrastructure Compute and install Anaconda Distribution, an open source tool for developing and testing machine learning models.
Anaconda is a general purpose tool for designing, building, and managing data science projects. With Anaconda, you have access to over 1,500 data science packages in R and Python. It manages libraries such as TensorFlow, NumPy, pandas, scikit-learn, and more. It also handles installing and updating machine learning environments such as Jupyter Notebook and RStudio.
This architecture shows a sample sandbox with several machine learning environments installed on a single compute instance in Oracle Cloud Infrastructure.
Each environment is independent and isolated from the others. Each can have its own version of Python, or R, or any other language, tooling, and library combination. This set up allows you to have several independent projects on one system where you can easily switch from one environment to the other.
Description of the illustration architecture-oci-compute-environments.png
Although expertise in machine learning and computer systems is not required to learn from this Solution, you should at least have some knowledge of technologies and processes used for collecting, moving, and transforming data.
Specifically, you should have the following skills:
Familiarity with Python.
Familiarity with Jupyter Notebook.
Some knowledge of Machine Learning processes and methods.
Familiarity with Linux command-line.
Ability to use SSH or PuTTY to connect to a remote machine.
About Required Services and Products
You must have access to Oracle Cloud Infrastructure Compute running Linux.
You can use either Oracle Linux 7.6 or Ubuntu 16.04. In this Solution we show you how to use both. We use the GPU compute shape VM.GPU3.1 which has one NVIDIA Tesla V100 GPU and 6 OCPUs, but you can also set up a sandbox on a non-GPU shape.
See Learn how to get Oracle Cloud services for Oracle Solutions to get the cloud services you need.