conclusion

Author: Sandeep Kumar

samples/04_gis_analysts_data_scientists/training_a_wind_turbine_detection_model_using_large_volume_of_training_data.ipynb

@@ -25,7 +25,8 @@
     "* [Model training](#Model-Training)\n",
     " * [Executing model training script](#Executing-model-training-script)\n",
     " * [Monitor model training](#Monitor-model-training)\n",
-    "* [Model inference](#Model-inference)"
+    "* [Model inference](#Model-inference)\n",
+    "* [Conclusion](#Conclusion)"
    ]
   },
   {
@@ -227,13 +228,6 @@
     "    zip_ref.extractall('.')"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -555,7 +549,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We will find the model saved in the 'models' folder. The saved model can be used to detect wind turbines using the [Detect Objects Using Deep Learning](https://pro.arcgis.com/en/pro-app/latest/tool-reference/image-analyst/detect-objects-using-deep-learning.htm) tool, available in both ArcGIS Pro and ArcGIS Enterprise."
+    "We will find the model saved in the 'models' folder. The saved model can be used to detect wind turbines using the [Detect Objects Using Deep Learning](https://pro.arcgis.com/en/pro-app/latest/tool-reference/image-analyst/detect-objects-using-deep-learning.htm) tool, available in both [ArcGIS Pro](https://www.esri.in/en-in/products/arcgis-pro/overview) and [ArcGIS Enterprise](https://enterprise.arcgis.com/en/)."
    ]
   },
   {
@@ -638,6 +632,20 @@
     "<center>A single wind turbine."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Conclusion"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This notebook has demonstrated a workflow to train a deep learning model that can detect features representing wind turbines. This notebook shows how multiprocessing can be used to the reduce time required to export training data. In this notebook we also leveraged multiple GPUs to reduce the time required for model training. A similar approach can be applied to classify other objects of interest, like trees, buildings, structures, etc."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},