AI Starter Kits

This is a curated collection of ready-to-use examples, best practices and learning materials, available to you in the form of interactive environments running on Neuro Platform.

With AI kits you can:

  • Run state of the art (SoTA) deep learning models for a variety of applied tasks
  • Interact with the results and extend the solution
  • Upload data, download the results using desktop or mobile device
  • Make your experiments reproducible

You can start by taking one of these kits and experimenting with it as a free tier user or by installing Neuro into your AWS, GCP or Azure cloud account or on-prem GPU rack.

What's Inside? #

Vision Kit #

Language Kit #

  • A Code-First Introduction to Natural Language Processing - everything you need to follow the NLP from including transfer learning for NLP, tips on working with languages other than English, attention and the transformer, text generation algorithms, issues of bias and some steps towards addressing them.

  • NLP - based on Microsoft's NLP Notebooks. Start building Natural Language Processing systems for the following scenarios: Topic Classification, Named Entity Recognition, Question Answering, Sentence Similarity and more.

Learn #

Prerequisites #

  • Familiarity with working with data in Python
  • Machine learning concepts (such as training and test sets)
  • Some experience with PyTorch and neural networks is helpful

Getting Started #

Clone the Repository #

git clone --recursive

Make sure to use --recursive argument to get a full copy of repositories included in the AI Kits.

Install Neuro CLI #

To work with AI Kits you need to install neuro CLI client.

Neuro CLI requires Python 3.7. We suggest installing Anaconda Python 3.7 Distribution. On some distributions you might have to run pip3 install -U neuromation.

pip install -U neuromation neuro login

Paste that in a macOS, Windows or Linux terminal prompt. This will automatically install Neuro CLI and initiate login flow.

Setup and Run AI Kit #

  • Navigate to the kit of interest: cd ai-kits/course-fast-ai-nlp
  • Setup the environment: make setup
  • Run Jupyter notebook: make jupyter