Apple provides developers with a number of ready-to-use machine learning models. Sometimes however, you need to create your own machine-learning model. The easiest way to do that is by using Turi Create.
- [Instructor] Core ML is driven by…the machine-learning models that we use, or that we create,…but sometimes the model that we need does not exist yet,…and for a long time, you needed to be a data scientist…to create working machine-learning models,…but with Turi Create, you can now easily create…your own custom models that exactly fit…the needs of your application,…so, let's quickly analyze the problem of our application,…and see how we can solve it, so what we have,…is a picture of a dog, and again,…we as humans have no problem identifying…the animal shown as a dog, but for a computer program,…that is a very challenging task, so,…what we want is an app that can take the image,…do some machine-learning magic,…and as a result we'd like to see if the image indeed…contains a dog, or a cat, and searching the Internet,…we couldn't find an existing machine-learning model…that solves the problem, so our solution…is building a custom machine-learning model,…or more exactly, a custom image classifier,…that is tailored to receive an input image,…
- Using Turi Create to create custom models
- Getting comfortable with Python
- Preparing data for Turi Create
- Creating a machine learning model with Turi Create
- Implementing an image picker controller
- Using Core ML and the Vision framework for image classification