Assembling workflows

KEY TERMS

A workflow carries the business logic that enables several analysis steps to be assembled together. These steps are first and foremost deep learning models for advanced image recognition tasks, but they are also logical steps for creating the information that best meets the business need.

Why do you need Deepomatic workflows?

In most cases, a suitable solution to a problem cannot be achieved by using a single neural network. This is indeed not the way to achieve the best performance and it is generally good practice to break down the overall problem into smaller steps. Deepomatic workflows give you this capacity.

You can create complex solutions without having to worry about deployment or runtime.

How to build your workflow?

A workflow corresponds to a configuration YAML file (called specs.yaml) associated to a more classic python project with one .py file per task group.

If it is the first time you are writing a workflow, please follow all the sub pages in order. It will show you how to efficiently implement, execute and test a workflow.