edit sagemaker-python-sdk/tensorflow_serving_using_elastic_inference_with_your_own_model/tensorflow_serving_pretrained_model_elastic_inference.ipynb

Author: EC2 Default User

sagemaker-python-sdk/tensorflow_serving_using_elastic_inference_with_your_own_model/tensorflow_serving_pretrained_model_elastic_inference.ipynb

@@ -114,7 +114,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Deploy the trained Model to an Endpoint with an attached EI accelerator\n",
+    "## Deploy the trained Model to an Endpoint with an attached EI accelerator\n",
     "\n",
     "The `deploy()` method creates an endpoint which serves prediction requests in real-time.\n",
     "\n",
@@ -148,7 +148,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#  Invoke the Endpoint to get inferences\n",
+    "##  Invoke the Endpoint to get inferences\n",
     "\n",
     "Invoking prediction:"
    ]
@@ -175,7 +175,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Delete the Endpoint\n",
+    "## Delete the Endpoint\n",
     "\n",
     "After you have finished with this example, remember to delete the prediction endpoint to release the instance(s) associated with it."
    ]