Diving into fastai with TactLabs.

Introduction

Hey there! This summer, I got the opportunity to take up a 30-day Learning Challenge with TactLabs and featurepreneur. The technology I chose for this particular Learning Challenge was fastai. Being a Machine Learning enthusiast, I really enjoyed Learning one of the best Deep Learning Libraries out there and I would like to share my experience and knowledge on the technology with you.

What is fastai?

fastai is a deep learning library that provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains. It also provides researchers with low-level components that can be mixed and matched to build new approaches.

You can install fastai on your own machines with conda as long as you’re running Linux or Windows.

fastai aims to do both things without compromising the ease of use, flexibility, or performance. This is possible due to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library.

Features of fastai

fastai includes:

• A new type dispatch system for Python along with a semantic type hierarchy for tensors
• A GPU-optimized computer vision library that can be extended in pure Python
• An optimizer which refactors out the common functionality of modern optimizers into two basic pieces, allowing optimization algorithms to be implemented in 4–5 lines of code
• A novel 2-way callback system that can access any part of the data, model, or optimizer and change it at any point during training
• A new data block API
• and much more.

fastai’s Layered API

Installing fastai on your machine

Installation for Miniconda

• If you’re using miniconda, then run:

conda install -c fastchan fastai

Installation for anaconda

• For anaconda, the command is:

conda install -c fastchan fastai anaconda

Installation using pip

• Or if you just want to use pip,

pip install fastai

Editable install

• If you are a budding developer and want to develop fastai yourself, you can install PyTorch and turn to download the editable install using:

git clone https://github.com/fastai/fastai
pip install -e "fastai[dev]"

More about fastai

fastai Documentation

To check out more about fastai, treat yourself to their intuitive docs using the links below:

• https://www.fast.ai
• https://www.fast.ai/2020/02/13/fastai-A-Layered-API-for-Deep-Learning/
• https://docs.fast.ai

My Learning Documentation

Feel free to check out my fastai Learning Documentation by following the link below:

• https://github.com/FabChris01/fast.ai

Conclusion

Thanks for stopping by!! I would like to thank Featurepreneur and Tactlabs for encouraging me to learn new developing technologies like fastai!! Do check out my other articles where I cover topics such as deep learning and other trending technologies.

Stay Safe!! Happy Learning!!

You can check out my Linkedin at https://www.linkedin.com/in/fabchris10/