Build an AI-powered Pet Detector with Python TensorFlow and Visual Studio Code – BRK3014




[ad_1]

Ever wondered what breed that dog or cat is? Let’s build a pet detector to recognize them in pictures! We will walk through the training, optimizing, and deploying of a deep learning model using Azure Notebooks and the Azure Machine Learning service. We will use transfer learning to retrain a MobileNet model using TensorFlow to recognize dog and cat breeds using the Oxford IIIT Pet Dataset. Next, we’ll optimize the model using Azure Machine Learning service to improve the model accuracy. Putting on our developer hat, we’ll then refactor the notebooks into Python modules using Visual Studio Code. Finally, we will deploy the model as a web service in Azure. See how Azure and Visual Studio Code has made AI and machine learning easy.

Source


[ad_2]

Comment List

  • Microsoft Developer
    November 25, 2020

    windows conference using macs lul

  • Microsoft Developer
    November 25, 2020

    Why no GitHup link? I mean you try usesing or inventing the newest trends but not have GitHup? XD

  • Microsoft Developer
    November 25, 2020

    Love this tutorial. It would be great if could expand on the class AMLConfig values in the setup file for the various Azure services that need to be filled in.

  • Microsoft Developer
    November 25, 2020

    Subtitles are all caps. This may cause text of the subtitles, to be only partially viewable. Microsoft should update subtitles. Perhaps AI with Python TensorFlow could assist.

Write a comment