catalog.us-east-1.prod.workshops.aws Open in urlscan Pro
2600:9000:225e:aa00:12:97a9:3c00:93a1  Public Scan

Form analysis
0 forms found in the DOM

Text Content

You need to enable JavaScript to run this app.

Settings

Amazon Lookout for Vision Workshop

--------------------------------------------------------------------------------

 * Lab 1 - Build model using console
    * Prerequisites - Start Cloud 9 Environment
    * Step 1 - Setup S3 bucket
    * Step 2 - Copy circuitboard dataset to S3
    * Step 3 - Create a project and dataset
    * Step 4 - Model Training and Performance Metrics
    * Step 5 - Model Evaluation and Feedback
    * Step 6 (Optional) - Model Retraining
    * Step 7 - Model Deployment and Use
    * Step 8 - Dashboard
    * Step 9 - Stopping the Model
    * Step10 - CloudWatch Metrics

 * Lab 2 - Build model using Python SDK
 * Lab 3 - Deploy model to edge device and run inferences
    * Prerequisites - Setting up your NVIDIA Jetson edge device
    * OPTIONAL - Take photos of subject for training data, train data, then
      export
    * Step 1 - Compile the model for the target edge device and package it as an
      AWS IoT GreenGrass component
    * Step 2 - Deploy the model to edge device using AWS IoT GreenGrass console
    * Step 3 - Run inferences on the edge device and post the inference metadata
      to AWS IoT MQTT
    * Step 4 - Cleanup

 * Lab 4 - Train and Deploy model to edge device and run inferences
    * Prerequisites - Setting up your NVIDIA Jetson edge device
    * Step 1 - Setup S3 bucket
    * Step 2 - Take photos of subject for training data, train data, then export
    * Step 3 - Create a project and dataset
    * Step 4 - Model Training and Performance Metrics
    * Step 5 - Model Evaluation and Feedback
    * Step 6 (Optional) - Model Retraining
    * Step 7 (Optional) - Model Retraining
    * Step 8 - Compile the model for the target edge device and package it as an
      AWS IoT GreenGrass component
    * Step 9 - Run inferences on the edge device and post the inference metadata
      to AWS IoT MQTT
    * Step 10 - Cleanup

 * Lab 5 - Train and Deploy Lookout For Vision On ADLINK DLAP Devices On Edge
    * Step 1 - Setting up your ADLINK/NVIDIA Jetson edge device
    * Step 2 - Setup S3 bucket
    * Step 3 - Take Training and Test pictures for dataset
    * Step 4 - Create a project and dataset
    * Step 5 - Model Training and Performance Metrics
    * Step 6 - Compile the model for the target edge device and package it as an
      AWS IoT Greengrass component
    * Step 7 Deploy Inference Components
    * Step 8 Cleanup

 * Lab 6 - UNDER DEVELOPMENT - Executing a Production Pilot Using Accelerator
   PoC Kit (APK)
    * Workflow 1 - Using the APK to collect training images and model training

 * Lab 7 - Identify the location of anomalies using Amazon Lookout for Vision at
   the edge without using a GPU

Content preferences
Language
English


 1. Amazon Lookout for Vision Workshop


AMAZON LOOKOUT FOR VISION WORKSHOP


WELCOME TO AMAZON LOOKOUT FOR VISION WORKSHOP

Amazon Lookout for Vision Workshop provides customers with hands-on experience
with Amazon Lookout for Vision features and APIs. It guides you to spot defects
and anomalies in visual representations using computer vision (CV). With Amazon
Lookout for Vision, manufacturing companies can increase quality and reduce
operational costs by quickly identifying differences in images of objects at
scale.


OVERVIEW OF THE LABS

 1. Build model using Lookout for Vision Console
 2. Build model using Lookout for Vision using Python SDK
 3. Deploy Lookout for Vision model to GreenGrass V2 device and run inferences

REFERENCE VIDEO:


Previous
Next

© 2008 - 2022, Amazon Web Services, Inc. or its affiliates. All rights
reserved.Privacy policyTerms of use
Settings

Settings

More


EVENT ENGINE DEBUG MENU



BUILD INFORMATION

Build Version 2022-10-21-21:16:40

Enable ConsoleLogSink