Skip to content

Create IBM Cloud Resources

Create IBM Cloud resources

This section shows you how to use Cloud Annotations to label a dataset of hard hat images with White / Blue / Yellow / Person objects

Lab Objectives

In this lab you will learn how to:

  • Create an instance of Cloud Object Storage (COS) in IBM Cloud
  • Upload the hard hat dataset to COS
  • Create Watson Machine Learning instance

Login to IBM Cloud

  • Visit IBM Cloud and, if you don't yet have an account, register for a (free) IBM Cloud Lite account. IBM Cloud login

Create a Cloud Object Storage instance

  • IBM Cloud will provision 25GB for free.
  • Visit the IBM Cloud Catalog COS page.
  • Click on the Create button COS Create

Create a Cloud Object Storage bucket

  • Click on the Create bucket button COS Create Bucket

  • Select a Standard predefined bucket

  • Name your bucket hardhat-detection-<your-initials>
  • The bucket name must be unique across the whole IBM Cloud Object Storage system COS Bucket name
  • Press the Next button
  • Unzip the hardhat-dataset.zip that was downloaded in the previous section.
  • Make certain you extract / unzip the .zip file.
  • Navigate to the extracted files on your computer
  • Drag the _annotations.json into the bucket.
  • A progress bar and a confirmation will display.
  • Hold off on uploading the images folder until the next step where you will be able to upload the entire folder.
  • Press the Next button.
  • On the next panel, scroll down and press the View bucket configuration button.
  • On the next panel, in the left navigation sidebar, click on Objects
  • Then, expand the Upload dropdown, and choose Folders COS Folder Upload
  • In the popup dialog, click on Select folders
  • A operating system file dialog will open, navigate and select the images folder that you have extracted.
  • A progress bar and a confirmation will display as the files are uploaded. COS Folder Upload
  • Congratulations - You have uploaded the hardhat model dataset to IBM Cloud Object Storage.

Create an Watson Machine Learning Instance

  • Visit the IBM Cloud Catalog
  • Search for Watson Machine Learning Catalog WML
  • Click on the Machine Learning tile WML Service
  • Click on the Create button WML Create
  • You now have a Watson Machine Learning instance which will be used to train your Hard Hat model. WML Instance

You are now ready to train your Tensorflow hard hat model, so proceed to the next Train Model section.