To complete this course, you will need a Google Cloud Platform Account. Your GCP account will be charged according to your usage. You must ensure that you have access to Google AI Platform from your GCP account. Before you start this hands-on project, you should be familiar with python programming and Google Cloud Platform. You should also have access to the custom-prediction routine feature of Google AI Platform. This 2-hour-long project-based course will teach you how to deploy and use a model on Google AI Platform. Normaly, any TensorFlow model can be deployed easily. You can upload a Saved Model to Google Storage and create an AI Platform model using it. In practice, TensorFlow may not be used as often as we would like. The AI Platform also allows for custom prediction procedures, so that's what we will be focusing on. Instead of converting a Keras model into a TensorFlow saved model, we will use the original h5 file. We will also be working with image data. This will allow us to explore the encoding and decoding byte data into strings for data transmission. Finally, we will encode the received data in our custom prediction procedure on the AI Platform, before we use it with our model. Coursera's hands on Rhyme project platform is where this course is run. Rhyme allows you to work in your browser in a hands-on way. Instant access to pre-configured cloud desktops that contain all the software and data needed for your project will be available. Everything is already configured in your Internet browser, so you can focus on learning. You'll have instant access to a cloud-based desktop with (e.g. Pre-installed Python, Jupyter and Tensorflow Note: This course is best for those who live in the North America region. We are currently working to offer the same experience in other areas.
