Custom Prediction Routine on Google AI Platform
Deploy a model with custom prediction routine on Google AI Platform.
Use a model deployed on Google AI Platform for inference.
Please note: You will need a Google Cloud Platform account to complete this course. Your GCP account will be charged as per your usage. Please make sure that you are able to access Google AI Platform within your GCP account. You should be familiar with python programming, and Google Cloud Platform before starting this hands on project. Please also ensure that you have access to the custom prediction routine feature in Google AI Platform. In this 2-hour long project-based course, you will learn how to deploy, and use a model on Google’s AI Platform. Normally, any model trained with the TensorFlow framework is quite easy to deploy, and you can simply upload a Saved Model on Google Storage, and create an AI Platform model with it. But, in practice, we may not always use TensorFlow. Fortunately, the AI Platform allows for custom prediction routines as well and that’s what we are going to focus on. Instead of converting a Keras model to a TensorFlow Saved Model, we will use the h5 file as is. Additionally, since we will be working with image data, we will use this opportunity to look at encoding and decoding of byte data into string for data transmission and then encoding of the received data in our custom prediction routine on the AI Platform before using it with our model. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your Internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with (e.g. Python, Jupyter, and Tensorflow) pre-installed. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
Habilidades que você desenvolverá
Aprender passo a passo
Em um vídeo reproduzido em uma tela dividida com a área de trabalho, seu instrutor o orientará sobre esses passos:
Introduction
Notebook Instance and Model Artifact
Testing the Model
Custom Prediction Class
Preprocessing
Postprocessing
Setup Script
Deploying the Model
Predictions
Como funcionam os projetos guiados
Sua área de trabalho é um espaço em nuvem, acessado diretamente do navegador, sem necessidade de nenhum download
Em um vídeo de tela dividida, seu instrutor te orientará passo a passo
Avaliações
Principais avaliações do CUSTOM PREDICTION ROUTINE ON GOOGLE AI PLATFORM
it was nice experience . the best thing you will learn that it is not much hard as wethink.
Coursera has a great opportunity to utilise for every one in course ... thank you coursera
Very excellent course for students and more quiz knowledge
good to start if you have basics of python adn tensorflow.
Perguntas Frequentes – FAQ
Perguntas Frequentes – FAQ
O que eu ganho se comprar projetos guiados?
Os projetos guiados estão disponíveis no computador e em dispositivos móveis?
Quem são os instrutores dos projetos guiados?
Posso baixar o trabalho do meu projeto guiado após completá-lo?
Como funciona a política de reembolso?Como funciona a política de reembolso?
Existe algum auxílio financeiro disponível?
Posso participar como ouvinte de um projeto guiado e assistir de graça a uma parte do vídeo?
Quanta experiência eu preciso ter para fazer esse projeto guiado?
Posso completar esse projeto guiado pelo meu navegador web em vez de instalar um software especial?
Como é a experiência de aprendizado com os projetos guiados?
Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.
Coursera Footer
