How to Get Started with REINVENT 3.2

May 30, 2021 | Data Science

Welcome to your step-by-step guide for installing and utilizing the REINVENT 3.2 project! While this repository is in archive mode and will no longer receive updates (with all further development happening on REINVENT 4), you can still leverage the power of this tool for your projects. Let’s dive right in!

Installation Steps

  • 1. Install Conda
  • 2. Clone this Git repository (run the command in your terminal)
  • 3. Open a terminal and navigate to the directory of the repository, then create the Conda environment:
  • $ conda env create -f reinvent.yml
  • 4. Activate the environment by running:
  • $ conda activate reinvent.v3.2
  • 5. You’re ready to use the tool!

System Requirements

Before using REINVENT, ensure your system meets the following requirements:

  • Python 3.7
  • A CUDA-enabled GPU
  • Operating System: Tested primarily on Linux

Utilizing Jupyter Notebooks

If you’re looking for some practical examples, there is another repository containing valuable Jupyter notebooks called ReinventCommunity. Keep in mind that it operates in a separate Conda environment, so you’ll need to set that up accordingly.

Usage Instructions

To execute running modes, follow these steps:

  • Run the desired example from the ReinventCommunity repo.
  • This will generate a template file for you.
  • Execute a running mode using the following command:
  • python input.py some_running_mode.json
  • Before executing, you can manually adjust the templates, primarily modifying file and folder paths as needed.
  • Most operations produce logs that are accessible via TensorBoard for performance monitoring.

Testing Your Setup

Testing is essential, and REINVENT uses the unittest framework. Here’s how you can set it up:

  • Create a config.json file in the configs directory of the project.
  • Use the included example.config.json as a blueprint by duplicating it and renaming it to config.json.
  • Once you’ve created the configuration, run REINVENT using:
  • python main_test.py
  • Ensure that the MAIN_TEST_PATH variable refers to a non-existent directory to avoid accidental deletion during tests.
  • Some tests require a proprietary OpenEye license. Set it up by directing the OE_LICENSE environment variable to the license file’s path.

Here’s a Creative Analogy

Imagine you’re a chef in a gourmet restaurant. REINVENT 3.2 is like your kitchen, and the various tools, ingredients, and recipes represent the functionalities it offers. Just as you meticulously follow a recipe to create a masterpiece dish, you’ll follow the installation and usage guide to harness the power of REINVENT.

The Conda environment is akin to your workstations, ensuring that everything is organized and ready for cooking. Each ingredient (or library) is essential for your dish, so having the right setups is crucial to avoid kitchen catastrophes!

Troubleshooting Tips

If you encounter issues during installation or usage, here are some troubleshooting ideas:

  • Double-check that all necessary system requirements are correctly installed.
  • Ensure that you have activated the correct Conda environment before running any commands.
  • If you face an issue with the OpenEye license, verify that the environment variable is set correctly and reboot your terminal session.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.

Stay Informed with the Newest F(x) Insights and Blogs

Tech News and Blog Highlights, Straight to Your Inbox