Merge branch 'master' into yong9856-performAnalysis

Author: Yongyao Jiang

guide/14-deep-learning/object-detection.ipynb

@@ -16,7 +16,18 @@
    },
    "source": [
     "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
-    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Export-Training-Samples\" data-toc-modified-id=\"Export-Training-Samples-1\">Export Training Samples</a></span></li><li><span><a href=\"#Data-Preparation\" data-toc-modified-id=\"Data-Preparation-2\">Data Preparation</a></span></li><li><span><a href=\"#Model-Training\" data-toc-modified-id=\"Model-Training-3\">Model Training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Train-SingleShotDetector-Model\" data-toc-modified-id=\"Train-SingleShotDetector-Model-3.1\">Train SingleShotDetector Model</a></span></li><li><span><a href=\"#Find-the-good-learning-rate\" data-toc-modified-id=\"Find-the-good-learning-rate-3.2\">Find the good learning rate</a></span></li><li><span><a href=\"#Train-the-model\" data-toc-modified-id=\"Train-the-model-3.3\">Train the model</a></span></li><li><span><a href=\"#Unfreezing-the-backbone-and-fine-tuning\" data-toc-modified-id=\"Unfreezing-the-backbone-and-fine-tuning-3.4\">Unfreezing the backbone and fine-tuning</a></span></li><li><span><a href=\"#Visualize-results\" data-toc-modified-id=\"Visualize-results-3.5\">Visualize results</a></span></li><li><span><a href=\"#Save-and-load-trained-models\" data-toc-modified-id=\"Save-and-load-trained-models-3.6\">Save and load trained models</a></span></li></ul></li><li><span><a href=\"#Deploy-trained-model\" data-toc-modified-id=\"Deploy-trained-model-4\">Deploy trained model</a></span></li><li><span><a href=\"#Model-management\" data-toc-modified-id=\"Model-management-5\">Model management</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-6\">Model inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-results\" data-toc-modified-id=\"Visualize-results-6.1\">Visualize results</a></span></li></ul></li></ul></div>"
+    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Prerequisites\" data-toc-modified-id=\"Prerequisites-1\">Prerequisites</a></span></li><li><span><a href=\"#Export-Training-Samples\" data-toc-modified-id=\"Export-Training-Samples-2\">Export Training Samples</a></span></li><li><span><a href=\"#Data-Preparation\" data-toc-modified-id=\"Data-Preparation-3\">Data Preparation</a></span></li><li><span><a href=\"#Model-Training\" data-toc-modified-id=\"Model-Training-4\">Model Training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Train-SingleShotDetector-Model\" data-toc-modified-id=\"Train-SingleShotDetector-Model-4.1\">Train SingleShotDetector Model</a></span></li><li><span><a href=\"#Find-the-good-learning-rate\" data-toc-modified-id=\"Find-the-good-learning-rate-4.2\">Find the good learning rate</a></span></li><li><span><a href=\"#Train-the-model\" data-toc-modified-id=\"Train-the-model-4.3\">Train the model</a></span></li><li><span><a href=\"#Unfreezing-the-backbone-and-fine-tuning\" data-toc-modified-id=\"Unfreezing-the-backbone-and-fine-tuning-4.4\">Unfreezing the backbone and fine-tuning</a></span></li><li><span><a href=\"#Visualize-results\" data-toc-modified-id=\"Visualize-results-4.5\">Visualize results</a></span></li><li><span><a href=\"#Save-and-load-trained-models\" data-toc-modified-id=\"Save-and-load-trained-models-4.6\">Save and load trained models</a></span></li></ul></li><li><span><a href=\"#Deploy-trained-model\" data-toc-modified-id=\"Deploy-trained-model-5\">Deploy trained model</a></span></li><li><span><a href=\"#Model-management\" data-toc-modified-id=\"Model-management-6\">Model management</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-7\">Model inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-results\" data-toc-modified-id=\"Visualize-results-7.1\">Visualize results</a></span></li></ul></li></ul></div>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prerequisites\n",
+    "- Export training samples and model inference requires [ArcGIS image server](https://www.esri.com/en-us/arcgis/products/arcgis-image-server). Inferencing against large image layers can be scaled out using multiple gpu enabled nodes. \n",
+    "- Data preparation, augmentation and model training workflows using `arcgis.learn` have a dependency on PyTorch and fast.ai deep learning libraries. They can be installed using conda as follows:\n",
+    "\n",
+    "`conda install -c fastai -c pytorch fastai=1.0.39 pytorch=1.0.0 torchvision`"
    ]
   },
   {
@@ -713,7 +724,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.2"
   },
   "toc": {
    "base_numbering": 1,

guide/14-deep-learning/pixel_based_classification.ipynb

@@ -14,7 +14,18 @@
    },
    "source": [
     "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
-    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Introduction\" data-toc-modified-id=\"Introduction-1\">Introduction</a></span></li><li><span><a href=\"#Export-training-data-for-deep-learning\" data-toc-modified-id=\"Export-training-data-for-deep-learning-2\">Export training data for deep learning</a></span><ul class=\"toc-item\"><li><span><a href=\"#Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS\" data-toc-modified-id=\"Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS-2.1\">Import ArcGIS API for Python and get connected to your GIS</a></span></li><li><span><a href=\"#Prepare-data-that-will-be-used-for-training-data-export\" data-toc-modified-id=\"Prepare-data-that-will-be-used-for-training-data-export-2.2\">Prepare data that will be used for training data export</a></span></li><li><span><a href=\"#Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data\" data-toc-modified-id=\"Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data-2.3\">Specify a folder name in raster store that will be used to store our training data</a></span></li><li><span><a href=\"#Export-training-data-using-arcgis.learn\" data-toc-modified-id=\"Export-training-data-using-arcgis.learn-2.4\">Export training data using <code>arcgis.learn</code></a></span></li></ul></li><li><span><a href=\"#Model-training\" data-toc-modified-id=\"Model-training-3\">Model training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-training-data\" data-toc-modified-id=\"Visualize-training-data-3.1\">Visualize training data</a></span></li><li><span><a href=\"#Load-model-architecture\" data-toc-modified-id=\"Load-model-architecture-3.2\">Load model architecture</a></span></li><li><span><a href=\"#Train-a-model-through-learning-rate-tuning-and-transfer-learning\" data-toc-modified-id=\"Train-a-model-through-learning-rate-tuning-and-transfer-learning-3.3\">Train a model through learning rate tuning and transfer learning</a></span></li><li><span><a href=\"#Visualize-classification-results-in-validation-set\" data-toc-modified-id=\"Visualize-classification-results-in-validation-set-3.4\">Visualize classification results in validation set</a></span></li></ul></li><li><span><a href=\"#Deployment-and-inference\" data-toc-modified-id=\"Deployment-and-inference-4\">Deployment and inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Locate-model-package\" data-toc-modified-id=\"Locate-model-package-4.1\">Locate model package</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-4.2\">Model inference</a></span></li></ul></li><li><span><a href=\"#Visualize-land-cover-classification-on-map\" data-toc-modified-id=\"Visualize-land-cover-classification-on-map-5\">Visualize land cover classification on map</a></span></li></ul></div>"
+    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Prerequisites\" data-toc-modified-id=\"Prerequisites-1\">Prerequisites</a></span></li><li><span><a href=\"#Introduction\" data-toc-modified-id=\"Introduction-2\">Introduction</a></span></li><li><span><a href=\"#Export-training-data-for-deep-learning\" data-toc-modified-id=\"Export-training-data-for-deep-learning-3\">Export training data for deep learning</a></span><ul class=\"toc-item\"><li><span><a href=\"#Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS\" data-toc-modified-id=\"Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS-3.1\">Import ArcGIS API for Python and get connected to your GIS</a></span></li><li><span><a href=\"#Prepare-data-that-will-be-used-for-training-data-export\" data-toc-modified-id=\"Prepare-data-that-will-be-used-for-training-data-export-3.2\">Prepare data that will be used for training data export</a></span></li><li><span><a href=\"#Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data\" data-toc-modified-id=\"Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data-3.3\">Specify a folder name in raster store that will be used to store our training data</a></span></li><li><span><a href=\"#Export-training-data-using-arcgis.learn\" data-toc-modified-id=\"Export-training-data-using-arcgis.learn-3.4\">Export training data using <code>arcgis.learn</code></a></span></li></ul></li><li><span><a href=\"#Model-training\" data-toc-modified-id=\"Model-training-4\">Model training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-training-data\" data-toc-modified-id=\"Visualize-training-data-4.1\">Visualize training data</a></span></li><li><span><a href=\"#Load-model-architecture\" data-toc-modified-id=\"Load-model-architecture-4.2\">Load model architecture</a></span></li><li><span><a href=\"#Train-a-model-through-learning-rate-tuning-and-transfer-learning\" data-toc-modified-id=\"Train-a-model-through-learning-rate-tuning-and-transfer-learning-4.3\">Train a model through learning rate tuning and transfer learning</a></span></li><li><span><a href=\"#Visualize-classification-results-in-validation-set\" data-toc-modified-id=\"Visualize-classification-results-in-validation-set-4.4\">Visualize classification results in validation set</a></span></li></ul></li><li><span><a href=\"#Deployment-and-inference\" data-toc-modified-id=\"Deployment-and-inference-5\">Deployment and inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Locate-model-package\" data-toc-modified-id=\"Locate-model-package-5.1\">Locate model package</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-5.2\">Model inference</a></span></li></ul></li><li><span><a href=\"#Visualize-land-cover-classification-on-map\" data-toc-modified-id=\"Visualize-land-cover-classification-on-map-6\">Visualize land cover classification on map</a></span></li></ul></div>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prerequisites\n",
+    "- Export training samples and model inference requires [ArcGIS image server](https://www.esri.com/en-us/arcgis/products/arcgis-image-server). Inferencing against large image layers can be scaled out using multiple gpu enabled nodes. \n",
+    "- Data preparation, augmentation and model training workflows using `arcgis.learn` have a dependency on PyTorch and fast.ai deep learning libraries. They can be installed using conda as follows:\n",
+    "\n",
+    "`conda install -c fastai -c pytorch fastai=1.0.39 pytorch=1.0.0 torchvision`"
    ]
   },
   {

samples/04_gis_analysts_data_scientists/detecting_swimming_pools_using_satellite_image_and_deep_learning.ipynb

@@ -16,7 +16,18 @@
    },
    "source": [
     "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
-    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Introduction-and-objective\" data-toc-modified-id=\"Introduction-and-objective-1\">Introduction and objective</a></span></li><li><span><a href=\"#Part-1---export-training-data-for-deep-learning\" data-toc-modified-id=\"Part-1---export-training-data-for-deep-learning-2\">Part 1 - export training data for deep learning</a></span><ul class=\"toc-item\"><li><span><a href=\"#Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS\" data-toc-modified-id=\"Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS-2.1\">Import ArcGIS API for Python and get connected to your GIS</a></span></li><li><span><a href=\"#Prepare-data-that-will-be-used-for-training-data-export\" data-toc-modified-id=\"Prepare-data-that-will-be-used-for-training-data-export-2.2\">Prepare data that will be used for training data export</a></span></li><li><span><a href=\"#Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data\" data-toc-modified-id=\"Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data-2.3\">Specify a folder name in raster store that will be used to store our training data</a></span></li><li><span><a href=\"#Export-training-data-using-arcgis.learn\" data-toc-modified-id=\"Export-training-data-using-arcgis.learn-2.4\">Export training data using <code>arcgis.learn</code></a></span></li></ul></li><li><span><a href=\"#Part-2---model-training\" data-toc-modified-id=\"Part-2---model-training-3\">Part 2 - model training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-training-data\" data-toc-modified-id=\"Visualize-training-data-3.1\">Visualize training data</a></span></li><li><span><a href=\"#Load-model-architecture\" data-toc-modified-id=\"Load-model-architecture-3.2\">Load model architecture</a></span></li><li><span><a href=\"#Train-a-model-through-learning-rate-tuning-and-transfer-learning\" data-toc-modified-id=\"Train-a-model-through-learning-rate-tuning-and-transfer-learning-3.3\">Train a model through learning rate tuning and transfer learning</a></span></li><li><span><a href=\"#Detect-and-visualize-swimming-pools-in-validation-set\" data-toc-modified-id=\"Detect-and-visualize-swimming-pools-in-validation-set-3.4\">Detect and visualize swimming pools in validation set</a></span></li></ul></li><li><span><a href=\"#Part-3---deployment-and-inference\" data-toc-modified-id=\"Part-3---deployment-and-inference-4\">Part 3 - deployment and inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Locate-model-package\" data-toc-modified-id=\"Locate-model-package-4.1\">Locate model package</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-4.2\">Model inference</a></span></li></ul></li><li><span><a href=\"#Conclusion\" data-toc-modified-id=\"Conclusion-5\">Conclusion</a></span></li><li><span><a href=\"#References\" data-toc-modified-id=\"References-6\">References</a></span></li></ul></div>"
+    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Prerequisites\" data-toc-modified-id=\"Prerequisites-1\">Prerequisites</a></span></li><li><span><a href=\"#Introduction-and-objective\" data-toc-modified-id=\"Introduction-and-objective-2\">Introduction and objective</a></span></li><li><span><a href=\"#Part-1---export-training-data-for-deep-learning\" data-toc-modified-id=\"Part-1---export-training-data-for-deep-learning-3\">Part 1 - export training data for deep learning</a></span><ul class=\"toc-item\"><li><span><a href=\"#Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS\" data-toc-modified-id=\"Import-ArcGIS-API-for-Python-and-get-connected-to-your-GIS-3.1\">Import ArcGIS API for Python and get connected to your GIS</a></span></li><li><span><a href=\"#Prepare-data-that-will-be-used-for-training-data-export\" data-toc-modified-id=\"Prepare-data-that-will-be-used-for-training-data-export-3.2\">Prepare data that will be used for training data export</a></span></li><li><span><a href=\"#Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data\" data-toc-modified-id=\"Specify-a-folder-name-in-raster-store-that-will-be-used-to-store-our-training-data-3.3\">Specify a folder name in raster store that will be used to store our training data</a></span></li><li><span><a href=\"#Export-training-data-using-arcgis.learn\" data-toc-modified-id=\"Export-training-data-using-arcgis.learn-3.4\">Export training data using <code>arcgis.learn</code></a></span></li></ul></li><li><span><a href=\"#Part-2---model-training\" data-toc-modified-id=\"Part-2---model-training-4\">Part 2 - model training</a></span><ul class=\"toc-item\"><li><span><a href=\"#Visualize-training-data\" data-toc-modified-id=\"Visualize-training-data-4.1\">Visualize training data</a></span></li><li><span><a href=\"#Load-model-architecture\" data-toc-modified-id=\"Load-model-architecture-4.2\">Load model architecture</a></span></li><li><span><a href=\"#Train-a-model-through-learning-rate-tuning-and-transfer-learning\" data-toc-modified-id=\"Train-a-model-through-learning-rate-tuning-and-transfer-learning-4.3\">Train a model through learning rate tuning and transfer learning</a></span></li><li><span><a href=\"#Detect-and-visualize-swimming-pools-in-validation-set\" data-toc-modified-id=\"Detect-and-visualize-swimming-pools-in-validation-set-4.4\">Detect and visualize swimming pools in validation set</a></span></li></ul></li><li><span><a href=\"#Part-3---deployment-and-inference\" data-toc-modified-id=\"Part-3---deployment-and-inference-5\">Part 3 - deployment and inference</a></span><ul class=\"toc-item\"><li><span><a href=\"#Locate-model-package\" data-toc-modified-id=\"Locate-model-package-5.1\">Locate model package</a></span></li><li><span><a href=\"#Model-inference\" data-toc-modified-id=\"Model-inference-5.2\">Model inference</a></span></li></ul></li><li><span><a href=\"#Visualize-detected-pools-on-map\" data-toc-modified-id=\"Visualize-detected-pools-on-map-6\">Visualize detected pools on map</a></span></li><li><span><a href=\"#Conclusion\" data-toc-modified-id=\"Conclusion-7\">Conclusion</a></span></li><li><span><a href=\"#References\" data-toc-modified-id=\"References-8\">References</a></span></li></ul></div>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prerequisites\n",
+    "- Export training samples and model inference requires [ArcGIS image server](https://www.esri.com/en-us/arcgis/products/arcgis-image-server). Inferencing against large image layers can be scaled out using multiple gpu enabled nodes. \n",
+    "- Data preparation, augmentation and model training workflows using `arcgis.learn` have a dependency on PyTorch and fast.ai deep learning libraries. They can be installed using conda as follows:\n",
+    "\n",
+    "`conda install -c fastai -c pytorch fastai=1.0.39 pytorch=1.0.0 torchvision`"
    ]
   },
   {
@@ -1144,7 +1155,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.4"
+   "version": "3.7.2"
   },
   "toc": {
    "base_numbering": 1,