Fix syntax + improve doc

aws · Sep 11, 2018 · 3919107 · 3919107
1 parent 326f713
commit 3919107
Showing 1 changed file with 19 additions and 16 deletions.
diff --git a/...on_to_amazon_algorithms/imageclassification_caltech/Image-classification-lst-format.ipynb b/...on_to_amazon_algorithms/imageclassification_caltech/Image-classification-lst-format.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Image classification training with image format demo\n",
+    "# Image classification training with image format\n",
     "\n",
     "1. [Introduction](#Introduction)\n",
     "2. [Prerequisites and Preprocessing](#Prequisites-and-Preprocessing)\n",
@@ -15,7 +15,7 @@
     "  2. [Training](#Training)\n",
     "4. [Deploy The Model](#Deploy-the-model)\n",
     "  1. [Create model](#Create-model)\n",
-    "  2. [Batch Transform](#Batch-transform)\n",
+    "  2. [Batch transform](#Batch-transform)\n",
     "  3. [Realtime inference](#Realtime-inference)\n",
     "    1. [Create endpoint configuration](#Create-endpoint-configuration) \n",
     "    2. [Create endpoint](#Create-endpoint) \n",
@@ -346,7 +346,7 @@
     "            \"DataSource\": {\n",
     "                \"S3DataSource\": {\n",
     "                    \"S3DataType\": \"S3Prefix\",\n",
-    "                    \"S3Uri\": s3train\n",
+    "                    \"S3Uri\": s3train,\n",
     "                    \"S3DataDistributionType\": \"FullyReplicated\"\n",
     "                }\n",
     "            },\n",
@@ -455,16 +455,15 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Set Up Hosting For The Model\n",
+    "## Deploy The Model\n",
     "\n",
     "A trained model does nothing on its own. We now want to use the model to perform inference. For this example, that means predicting the class label given an input image.\n",
     "\n",
     "This section involves several steps,\n",
     "\n",
     "1. [Create model](#CreateModel) - Create model for the training output\n",
-    "1. [Create endpoint configuration](#CreateEndpointConfiguration) - Create a configuration defining an endpoint.\n",
-    "1. [Create endpoint](#CreateEndpoint) - Use the configuration to create an inference endpoint.\n",
-    "1. [Perform inference](#Perform Inference) - Perform inference on some input data using the endpoint."
+    "1. [Batch Transform](#BatchTransform) - Create a transform job to perform batch inference.\n",
+    "1. [Host the model for realtime inference](#HostTheModel) - Create an inference endpoint and perform realtime inference."
    ]
   },
   {
@@ -524,7 +523,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   }, 
    "outputs": [],
    "source": [
     "timestamp = time.strftime('-%Y-%m-%d-%H-%M-%S', time.gmtime())\n",
@@ -564,7 +565,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },   
    "outputs": [],
    "source": [
     "sagemaker = boto3.client('sagemaker')\n",
@@ -620,14 +623,14 @@
     "    print(\"Result: label - \" + object_categories[index] + \", probability - \" + str(probability))\n",
     "    return object_categories[index], probability\n",
     "\n",
-    "inpute_images = list_objects(s3_client, bucket, urlparse(batch_input).path.lstrip('/'))\n",
-    "print(\"Sample inputs: \" + str(input_images[:2]))\n",
+    "inputs = list_objects(s3_client, bucket, urlparse(batch_input).path.lstrip('/'))\n",
+    "print(\"Sample inputs: \" + str(inputs[:2]))\n",
     "\n",
     "outputs = list_objects(s3_client, bucket, batch_job_name + \"/output\")\n",
     "print(\"Sample output: \" + str(outputs[:2]))\n",
     "\n",
-    "# Check prediction result of the first 3 images\n",
-    "[get_label(s3_client, bucket, prefix) for prefix in outputs[0:3]]"
+    "# Check prediction result of the first 2 images\n",
+    "[get_label(s3_client, bucket, prefix) for prefix in outputs[0:2]]"
    ]
   },
   {
@@ -684,7 +687,7 @@
    "metadata": {},
    "source": [
     "#### Create endpoint\n",
-    "Lastly, the customer creates the endpoint that serves up the model, through specifying the name and configuration defined above. The end result is an endpoint that can be validated and incorporated into production applications. This takes 9-11 minutes to complete."
+    "Next, the customer creates the endpoint that serves up the model, through specifying the name and configuration defined above. The end result is an endpoint that can be validated and incorporated into production applications. This takes 9-11 minutes to complete."
    ]
   },
   {
@@ -761,7 +764,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Perform inference\n",
+    "#### Perform inference\n",
     "Finally, the customer can now validate the model for use. They can obtain the endpoint from the client library using the result from previous operations, and generate classifications from the trained model using that endpoint.\n"
    ]
   },
@@ -781,7 +784,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Download test image"
+    "##### Download test image"
    ]
   },
   {