Examples on how to use SageMaker’s built-in algorithms.

Image processing

SageMaker provides algorithms that are used for image processing.

image_classification

• Using SageMaker Image Classification with Amazon Elastic Inference
• Training
• Deploy The Model
• Image classification training with image format
• End-to-End Incremental Training Image Classification Example
• Inference
• Image classification training with image format demo
• Inference
• Image classification transfer learning demo
• Training
• Deploy The Model
• Image classification transfer learning demo
• Inference
• End-to-End Multiclass Image Classification Example
• Training
• Deploy The Model
• End-to-End Multiclass Image Classification Example
• Compile
• Inference
• Image classification multi-label classification
• Inference

object_detection

• Amazon SageMaker Object Detection for Bird Species
• Data Preparation
• Understand the dataset
• Generate RecordIO files
• Train the model
• Host the model
• Test the model
• Clean up
• Improve the model
• Amazon SageMaker Object Detection Incremental Training
• Amazon SageMaker Object Detection using the Image and JSON format
• Amazon SageMaker Object Detection using the RecordIO format

semantic_segmentation

• Amazon SageMaker Semantic Segmentation Algorithm
• Hosting

Text processing

SageMaker provides algorithms that are tailored to the analysis of texts and documents used in natural language processing and translation.

blazingtext

• Introduction
• Setup
• Data Preprocessing
• Training
• Training the BlazingText model for supervised text classification
• Hosting / Inference
• Introduction
• Setup
• Training Setup
• Training the BlazingText model for generating word vectors
• Hosting / Inference
• Introduction
• Setup
• Training Setup
• Training the BlazingText model for generating word vectors
• Hosting / Inference

lda

• An Introduction to SageMaker LDA
• Introduction
• Setup
• Training
• Inference
• Epilogue

ntm

• Amazon SageMaker Neural Topic Model now supports auxiliary vocabulary channel, new topic evaluation metrics, and training subsampling
• Conclusion
• Introduction to Basic Functionality of NTM
• Contents
• Introduction
• Setup
• Data
• Training
• Inference
• Extensions
• An Introduction to SageMaker Neural Topic Model
• Introduction
• Data Preparation
• Model Training
• Model Hosting and Inference
• Model Exploration

seq2seq

• Machine Translation English-German Example Using SageMaker Seq2Seq
• Perform Inference
• Stop / Close the Endpoint (Optional)

Time series processing

SageMaker DeepAR algorithm is useful for processing time series data.

deepar

• Time series forecasting with DeepAR - Synthetic data
• SageMaker/DeepAR demo on electricity dataset
• Additional features
• Predicting driving speed violations with the Amazon SageMaker DeepAR algorithm

linear_learner

• Time Series Forecasting with Linear Learner

Supervised learning algorithms

Amazon SageMaker provides several built-in general purpose algorithms that can be used for either classification or regression problems.

factorization_machines

• An Introduction to Factorization Machines with MNIST

knn

• Introduction
• Part 1: Running kNN in 5 minutes
• Part 2: Deep dive, Tuning kNN

linear_learner

• An Introduction to Linear Learner with MNIST
• Train Linear Learner model using File System Data Source
• Build multiclass classifiers with Amazon SageMaker linear learner
• Fairness Linear Learner in SageMaker

xgboost

Basic

• Multiclass classification with Amazon SageMaker XGBoost algorithm
• Set up hosting for the model
• Regression with Amazon SageMaker XGBoost algorithm
• Customer Churn Prediction with XGBoost
• Targeting Direct Marketing with Amazon SageMaker XGBoost

Advanced

• Regression with Amazon SageMaker XGBoost algorithm
• Regression with Amazon SageMaker XGBoost (Parquet input)

Unsupervised learning algorithms

Amazon SageMaker provides several built-in algorithms that can be used for a variety of unsupervised learning tasks such as clustering, dimension reduction, pattern recognition, and anomaly detection.

ip_insights

• An Introduction to the Amazon SageMaker IP Insights Algorithm

kmeans

• Analyze US census data for population segmentation using Amazon SageMaker
• End-to-End Example #1
• End-to-End Example #1

pca

• An Introduction to PCA with MNIST

rcf

• An Introduction to SageMaker Random Cut Forests
• Introduction
• Setup
• Training
• Inference
• Epilogue

Feature engineering

object2vec

• Document Embedding with Amazon SageMaker Object2Vec
• An Introduction to SageMaker ObjectToVec model for MovieLens recommendation
• Background
• Data exploration and preparation
• Rating prediction task
• Recommendation task
• An Introduction to SageMaker ObjectToVec model for sequence-sequence embedding
• Background
• Transfer learning
• How to enable the optimal training result
• Hyperparameter Tuning (Advanced)