From the course: Building and Deploying Deep Learning Applications with TensorFlow

Unlock the full course today

Join today to access over 22,700 courses taught by industry experts or purchase this course individually.

Host your model in the cloud with Google Cloud

Host your model in the cloud with Google Cloud - TensorFlow Tutorial

From the course: Building and Deploying Deep Learning Applications with TensorFlow

Start my 1-month free trial

Host your model in the cloud with Google Cloud

“

- [Instructor] The advantage of hosting your model in the Google Cloud is that it is accessible from anywhere in the world. Google servers will run the model, and you are only charged based on how many requests are made. It's a great option for using a TensorFlow model in production if you don't want to maintain your own servers. Let's learn how to upload a custom TensorFlow model to the Google Cloud ML service. Before we get started, make sure you have already exported the model as a .pb file. You can do that by running export_model_for_cloud final in PyCharm, if you haven't already. Also, make sure that you have a properly configured Google Cloud account, with access to the Google Cloud ML service, and that you have the gcloud command line tool already installed. You can review the previous video if you don't have those two things available yet. I have my machine learning model exported here, to the exported_model subfolder. To use this model in the Cloud, it's a two-step process…

Contents