Getting started
PreFab leverages deep learning to model fabrication-induced structural variations in integrated photonic devices. Through this virtual nanofabrication environment, we uncover valuable insights into nanofabrication processes and enhance device design accuracy.
This guide will get you all set up and ready to use PreFab to predict the fabrication-induced structural variations of your own integrated photonic devices.
Install PreFab
Before making your first prediction, follow the steps below to install the PreFab Python package.
From PyPI
You can easily install PreFab using pip, which is the Python package installer. This method is suitable for most users.
From GitHub
For those who wish to make changes to the source code for their own development purposes, PreFab can also be installed directly from GitHub.
Authenticate PreFab token
To link your PreFab account to the API, you will need to create an authentication token. You can do this by running the following command in your terminal. This will open a browser window where you can log in and generate a token.
PreFabricate your designs
See the following guides to get started with making your first predictions and corrections of fabrication-induced variations with PreFab:
If you are new to Python, we recommend starting with the Python for Photonics blog post.
Performance and usage
PreFab models are served via a serverless cloud platform. Please note:
- 🐢 CPU inference may result in slower performance. Future updates will introduce GPU inference.
- 🥶 The first prediction may take longer due to cold start server loading. Subsequent predictions will be faster.
- 😊 Be considerate of usage. Start small and limit usage during the initial stages. Thank you!
Your thoughts are valuable
PreFab is a new design tool, still in its early days, that we hope will become useful to the photonics community. We are eager to hear about your experiences with PreFab. Please share your thoughts with us and any issues you may have on GitHub.
Happy designing
-
For more information, visit our Privacy Policy and Terms of Service. ↩