Deep Learning (DL) methods are increasingly recognised as powerful analytical tools for microscopy. Their potential to outperform conventional image processing pipelines is now well established. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources, install multiple computational tools and modify code instructions to train neural networks all lead to an accessibility barrier that novice users often find difficult to cross. Here, we present ZeroCostDL4Mic, an entry-level teaching and deployment DL platform which considerably simplifies access and use of DL for microscopy. It is based on Google Colab which provides the free, cloud-based computational resources needed. ZeroCostDL4Mic allows researchers with little or no coding expertise to quickly test, train and use popular DL networks. In parallel, it guides researchers to acquire more knowledge, to experiment with optimising DL parameters and network architectures. We also highlight the limitations and requirements to use Google Colab. Altogether, ZeroCostDL4Mic accelerates the uptake of DL for new users and promotes their capacity to use increasingly complex DL networks.
Read our preprint on biorxiv
Access ZeroCostDL4Mic on github
Lucas von Chamier, Romain F. Laine, Johanna Jukkala, Christoph Spahn, Daniel Krentzel, Elias Nehme, Martina Lerche, Sara Hernández-Pérez, Pieta K. Mattila, Eleni Karinou, Séamus Holden, Ahmet Can Solak, Alexander Krull, Tim-Oliver Buchholz, Martin L. Jones, Loïc A Royer, Christophe Leterrier, Yoav Shechtman, Florian Jug, Mike Heilemann, Guillaume Jacquemet, Ricardo Henriques