diff --git a/IoT Edge anomaly detection tutorial/00-anomaly-detection-tutorial.ipynb b/IoT Edge anomaly detection tutorial/00-anomaly-detection-tutorial.ipynb index 85c3bd9..195bd5c 100644 --- a/IoT Edge anomaly detection tutorial/00-anomaly-detection-tutorial.ipynb +++ b/IoT Edge anomaly detection tutorial/00-anomaly-detection-tutorial.ipynb @@ -404,7 +404,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Create the driver file. Note that the `model.pkl` file in the get_model_path call is referring to a model named `model.pkl` registered under the workspace (what you registered above). It is NOT referenceing the local file." + "Create the driver file. Note that the `model.pkl` file in the get_model_path call is referring to a model named `model.pkl` registered under the workspace (what you registered above). It is NOT referencing the local file." ] }, { @@ -658,7 +658,9 @@ "metadata": {}, "source": [ "## 6: Deploy container to Azure IoT Edge device\n", - "Create a deployment.json file that contains the modules you want to deploy to the device and the routes. Then push this file to the IoT Hub, which will then send it to the IoT Edge device. The IoT Edge agent will then pull the Docker images and run them." + "Create a deployment.json file that contains the modules you want to deploy to the device and the routes. Then push this file to the IoT Hub, which will then send it to the IoT Edge device. The IoT Edge agent will then pull the Docker images and run them.\n", + "\n", + "This section pulls the container registry information from your workspace. Machine Learning workspaces don't automatically provision container registries when they're created, but wait until there's a container image to store. In the case of this tutorial, the container image was created in section 4.2. So in this section, we update the workspace config information. Your container registry still may not be ready by the time you get to this step. Keep running the first cell of this section until it finds the registry information. You can also check to see if the container registry exists yet by viewing the workspace overview page in the Azure portal." ] }, { @@ -667,6 +669,9 @@ "metadata": {}, "outputs": [], "source": [ + "# Update the workspace object\n", + "ws = Workspace.from_config()\n", + "\n", "# Getting your container details\n", "container_reg = ws.get_details()[\"containerRegistry\"]\n", "reg_name=container_reg.split(\"/\")[-1]\n",