create tabler of contents notebooks

aws · Jun 10, 2022 · a32f83f · a32f83f
1 parent 92ed8c6
commit a32f83f
Show file tree

Hide file tree

Showing 10 changed files with 881 additions and 0 deletions.
diff --git a/inference/bring_your_own_container.ipynb b/inference/bring_your_own_container.ipynb
@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BYOC\n",
+    "\n",
+    "Examples on how to use your own model serving containers or extend pre-built containers on SageMaker."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TensorFlow\n",
+    "---\n",
+    "\n",
+    "### Elastic inference\n",
+    "\n",
+    "* [Using Amazon Elastic Inference with a pre-trained TensorFlow Serving model on SageMaker](../sagemaker-python-sdk/tensorflow_serving_using_elastic_inference_with_your_own_model/tensorflow_serving_pretrained_model_elastic_inference.ipynb)\n",
+    "\n",
+    "### TensorFlow Serving container\n",
+    "\n",
+    "* [Using the SageMaker TensorFlow Serving Container](../sagemaker-python-sdk/tensorflow_serving_container/tensorflow_serving_container.ipynb)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "instance_type": "ml.t3.medium",
+  "kernelspec": {
+   "display_name": "Python 3 (Data Science)",
+   "language": "python",
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/datascience-1.0"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/inference/data_types.ipynb b/inference/data_types.ipynb
@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Data Types"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Image\n",
+    "---\n",
+    "\n",
+    "* [MNIST Training using PyTorch](../sagemaker-python-sdk/pytorch_mnist/pytorch_mnist.ipynb)\n",
+    "* [Using the SageMaker TensorFlow Serving Container](../sagemaker-python-sdk/tensorflow_serving_container/tensorflow_serving_container.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tabular\n",
+    "---\n",
+    "\n",
+    "* [Iris Training and Prediction with Sagemaker Scikit-learn](../sagemaker-python-sdk/scikit_learn_iris/scikit_learn_estimator_example_with_batch_transform.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Text\n",
+    "---\n",
+    "\n",
+    "* [Hosting and Deployment of Pre-Trained Text Models using SageMaker Endpoint and BlazingText](../introduction_to_amazon_algorithms/blazingtext_hosting_pretrained_fasttext/blazingtext_hosting_pretrained_fasttext.ipynb)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Time series\n",
+    "---\n",
+    "\n",
+    "* [Time series forecasting with DeepAR - Synthetic data](../introduction_to_amazon_algorithms/deepar_synthetic/deepar_synthetic.ipynb)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "instance_type": "ml.t3.medium",
+  "kernelspec": {
+   "display_name": "Python 3 (Data Science)",
+   "language": "python",
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/datascience-1.0"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/inference/endpoints.ipynb b/inference/endpoints.ipynb
@@ -0,0 +1,59 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Get started with endpoints\n",
+    "\n",
+    "Examples on how to use your own model serving containers or extend pre-built containers on SageMaker.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## A/B testing\n",
+    "---\n",
+    "\n",
+    "* [A/B Testing with Amazon SageMaker](../sagemaker_endpoints/a_b_testing/a_b_testing.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Multi-model endpoints\n",
+    "---\n",
+    "\n",
+    "* [Amazon SageMaker Multi-Model Endpoints using Scikit Learn](../advanced_functionality/multi_model_sklearn_home_value/sklearn_multi_model_endpoint_home_value.ipynb)\n",
+    "* [Amazon SageMaker Multi-Model Endpoints using XGBoost](../advanced_functionality/multi_model_xgboost_home_value/xgboost_multi_model_endpoint_home_value.ipynb)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "instance_type": "ml.t3.medium",
+  "kernelspec": {
+   "display_name": "Python 3 (Data Science)",
+   "language": "python",
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/datascience-1.0"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/inference/index.ipynb b/inference/index.ipynb
@@ -0,0 +1,104 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Deploy Models with SageMaker\n",
+    "\n",
+    "Examples on how to host models for predictions, inference, and transformations with SageMaker."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Bring your own container\n",
+    "---\n",
+    "\n",
+    "* [Bring Your Own Container (BYOC)](bring_your_own_container.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Data types\n",
+    "---\n",
+    "\n",
+    "* [Data Types](data_types.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Model deployment\n",
+    "---\n",
+    "\n",
+    "* [Use Your Own Inference Code with Amazon SageMaker XGBoost Algorithm](../introduction_to_amazon_algorithms/xgboost_abalone/xgboost_inferenece_script_mode.ipynb)\n",
+    "* [TensorFlow BYOM: Train locally and deploy on SageMaker.](../advanced_functionality/tensorflow_iris_byom/tensorflow_BYOM_iris.ipynb)\n",
+    "* [Bring Your Own Model (k-means)](../advanced_functionality/kmeans_bring_your_own_model/kmeans_bring_your_own_model.ipynb)\n",
+    "* [Amazon SageMaker XGBoost Bring Your Own Model](../advanced_functionality/xgboost_bring_your_own_model/xgboost_bring_your_own_model.ipynb)\n",
+    "\n",
+    "### Elastic inference\n",
+    "\n",
+    "* [Using Amazon Elastic Inference with MXNet on Amazon SageMaker](../sagemaker-python-sdk/mxnet_mnist/mxnet_mnist_elastic_inference.ipynb)\n",
+    "* [Using Amazon Elastic Inference with MXNet on an Amazon SageMaker Notebook Instance](../sagemaker-python-sdk/mxnet_mnist/mxnet_mnist_elastic_inference_local.ipynb)\n",
+    "* [Hosting ONNX models with Amazon Elastic Inference](../sagemaker-python-sdk/mxnet_onnx_eia/mxnet_onnx_eia.ipynb)\n",
+    "\n",
+    "\n",
+    "### Endpoints\n",
+    "\n",
+    "* [Endpoints](endpoints.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Multi-Model Deployment\n",
+    "---\n",
+    "\n",
+    "* [Amazon SageMaker Multi-Model Endpoints using Scikit Learn](../advanced_functionality/multi_model_sklearn_home_value/sklearn_multi_model_endpoint_home_value.ipynb)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Nvidia Triton Inference\n",
+    "---\n",
+    "\n",
+    "* [Triton on SageMaker - Deploying a PyTorch Resnet50 model](../sagemaker-triton/resnet50/triton_resnet50.ipynb)\n",
+    "* [Triton on SageMaker - NLP Bert](../sagemaker-triton/nlp_bert/triton_nlp_bert.ipynb)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (Data Science)",
+   "language": "python",
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/datascience-1.0"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/label_data/index.ipynb b/label_data/index.ipynb
@@ -14,6 +14,7 @@
    "metadata": {},
    "source": [
     "## Get started with Ground Truth\n",
+    "---\n",
     "\n",
     "[This video](https://www.youtube.com/embed/_FPI6KjDlCI) shows you how to setup and use Amazon SageMaker Ground Truth. (Length: 9:37)\n",
     "\n",
@@ -27,6 +28,7 @@
    "metadata": {},
    "source": [
     "## Task types\n",
+    "---\n",
     "\n",
     "### 3D point clouds\n",
     "* [Create a 3D Point Cloud Labeling Job with Amazon SageMaker Ground Truth](../ground_truth_labeling_jobs/3d_point_cloud_demo/create-3D-pointcloud-labeling-job.ipynb)\n",
@@ -50,6 +52,7 @@
    "metadata": {},
    "source": [
     "## Bring your own model\n",
+    "---\n",
     "\n",
     "* [Create an Active Learning Workflow using Amazon SageMaker Ground Truth](../ground_truth_labeling_jobs/bring_your_own_model_for_sagemaker_labeling_workflows_with_active_learning/bring_your_own_model_for_sagemaker_labeling_workflows_with_active_learning.ipynb)\n"
    ]
@@ -59,6 +62,7 @@
    "metadata": {},
    "source": [
     "## Analysis tasks\n",
+    "---\n",
     "\n",
     "### Data analysis of image classification\n",
     "* [Data Analysis Using a Ground Truth Image Classification Output Manifest](../ground_truth_labeling_jobs/data_analysis_of_ground_truth_image_classification_output/data_analysis_of_ground_truth_image_classification_output.ipynb)\n"