Difference between revisions of "Getting Started & Project: Object Detection"
(Created page with "[http://www.youtube.com/results?search_query=amazon+deeplens YouTube search...] * [http://aws.amazon.com/deeplens/ Product page...] * [http://medium.com/@julsimon/exploring-a...") |
m (Text replacement - "http:" to "https:") |
||
| (16 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | [ | + | {{#seo: |
| + | |title=PRIMO.ai | ||
| + | |titlemode=append | ||
| + | |keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS | ||
| + | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
| + | }} | ||
| + | [https://www.youtube.com/results?search_query=amazon+deeplens+Object+Detection YouTube search...] | ||
| + | [https://www.google.com/search?q=amazon+deeplens+Object+Detection+deep+machine+learning+ML+artificial+intelligence ...Google search] | ||
| − | * [ | + | * [[Image Retrieval / Object Detection]] |
| − | * [ | + | * [[DeepLens - deep learning enabled video camera]] |
| − | + | * [[More DeepLens Projects]] | |
| − | + | * [https://aws.amazon.com/deeplens/ Product page...] | |
| + | * [https://forums.aws.amazon.com/forum.jspa?forumID=275 DeepLens Discussion Forum | AWS] | ||
| − | + | == I just got my DeepLens! == | |
| − | == | + | * [https://aws.amazon.com/deeplens/resources/ DeepLens Developer Resources | AWS] |
| + | ** [https://aws.amazon.com/getting-started/tutorials/configure-aws-deeplens/ Configure Your New AWS DeepLens] | ||
| + | ** [https://aws.amazon.com/getting-started/tutorials/build-deeplens-project-sagemaker/?trk=gs_card Build an AWS DeepLens Project] | ||
| + | ** [https://aws.amazon.com/getting-started/tutorials/create-deploy-project-deeplens/?trk=gs_card Creating and Deploying an AWS DeepLens Project] | ||
| + | ** [https://aws.amazon.com/getting-started/tutorials/extend-deeplens-project/?trk=gs_card Extending Your AWS DeepLens Project] | ||
| + | * [https://blog.kloud.com.au/2018/02/27/aws-deeplens-part-1-getting-the-deeplens-online/ Part 1 - Getting Online | SAMZAKKOUR @ Kloud] | ||
| + | * [https://www.lynda.com/Amazon-Web-Services-tutorials/Setting-up-your-AWS-DeepLens/706932/737910-4.html Lynda.com Setting up your AWS DeepLens] | ||
| − | + | Thoughts: Instructions are unclear on: [1] what computer to use when, [2] what network to link, [3] no signature is required on the streaming certificate which is to be loaded into each browser - file is named 'download'. There’s a known bug that prevents the DeepLens from connecting to Wi-Fi networks that have non-alphanumeric characters (e.g. spaces). | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | + | <youtube>j0DkaM4L6n4</youtube> | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | + | == First Project: Object Detection == | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | == | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
*[[(Deep) Residual Network (DRN) - ResNet]] | *[[(Deep) Residual Network (DRN) - ResNet]] | ||
| − | [ | + | [https://docs.aws.amazon.com/deeplens/latest/dg/deeplens-templated-projects-overview.html This project] shows you how a deep learning model can detect and recognize objects in a room. The project uses the Single Shot MultiBox Detector (SSD) framework (Reference: [[Image Retrieval / Object Detection]]; Faster Region-based Convolutional Neural Networks (R-CNN), You only Look Once (YOLO), Single Shot Detector(SSD) to detect objects with a pretrained [[ResNet-50]] network on a [[MXNet]] framework. The network has been trained on the [https://host.robots.ox.ac.uk/pascal/VOC Pascal Visual Object Classes Challenge (VOC)] dataset and is capable of recognizing 20 different kinds of objects. The model takes the video stream from your AWS DeepLens device as input and labels the objects that it identifies. The project uses a pretrained optimized model that is ready to be deployed to your AWS DeepLens device. After deploying it, you can watch your AWS DeepLens model recognize objects around you. The model is able to recognize the following objects: airplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, potted plant, sheep, sofa, train, and TV monitor. |
| − | Your web browser is the interface between you and your AWS DeepLens device. You perform all of the following activities on the AWS DeepLens console using your browser, open the AWS DeepLens console at [ | + | Your web browser is the interface between you and your AWS DeepLens device. You perform all of the following activities on the AWS DeepLens console using your browser, open the AWS DeepLens console at [https://console.aws.amazon.com/deeplens/ https://console.aws.amazon.com/deeplens]. AWS [[Lambda]] function renders bounding boxes around detected objects (with ≥25% confidence by default) and sends [https://www.w3schools.com/js/js_json.asp JSON]-formatted messages with detected object types and corresponding confidence levels to an AWS IoT [[MQTT]] topic. For a walkthrough...[https://github.com/awsdocs/aws-deeplens-user-guide/blob/master/doc_source/deeplens-create-deploy-sample-project.md Creating and Deploying an AWS DeepLens Sample Project | GitHub] |
<youtube>xzFwySJYRoE</youtube> | <youtube>xzFwySJYRoE</youtube> | ||
| Line 96: | Line 43: | ||
<youtube>PbQO3-jYkGo</youtube> | <youtube>PbQO3-jYkGo</youtube> | ||
| − | == SSH == | + | == SSH to DeepLens == |
| − | * [ | + | * [https://www.deeplearning.team Deep Learning Team | Jovon Weathers] |
<youtube>2eKjcLsBH6E</youtube> | <youtube>2eKjcLsBH6E</youtube> | ||
<youtube>HozP1t3usPM</youtube> | <youtube>HozP1t3usPM</youtube> | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
Latest revision as of 14:52, 28 March 2023
YouTube search... ...Google search
- Image Retrieval / Object Detection
- DeepLens - deep learning enabled video camera
- More DeepLens Projects
- Product page...
- DeepLens Discussion Forum | AWS
I just got my DeepLens!
- DeepLens Developer Resources | AWS
- Part 1 - Getting Online | SAMZAKKOUR @ Kloud
- Lynda.com Setting up your AWS DeepLens
Thoughts: Instructions are unclear on: [1] what computer to use when, [2] what network to link, [3] no signature is required on the streaming certificate which is to be loaded into each browser - file is named 'download'. There’s a known bug that prevents the DeepLens from connecting to Wi-Fi networks that have non-alphanumeric characters (e.g. spaces).
First Project: Object Detection
This project shows you how a deep learning model can detect and recognize objects in a room. The project uses the Single Shot MultiBox Detector (SSD) framework (Reference: Image Retrieval / Object Detection; Faster Region-based Convolutional Neural Networks (R-CNN), You only Look Once (YOLO), Single Shot Detector(SSD) to detect objects with a pretrained ResNet-50 network on a MXNet framework. The network has been trained on the Pascal Visual Object Classes Challenge (VOC) dataset and is capable of recognizing 20 different kinds of objects. The model takes the video stream from your AWS DeepLens device as input and labels the objects that it identifies. The project uses a pretrained optimized model that is ready to be deployed to your AWS DeepLens device. After deploying it, you can watch your AWS DeepLens model recognize objects around you. The model is able to recognize the following objects: airplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, potted plant, sheep, sofa, train, and TV monitor.
Your web browser is the interface between you and your AWS DeepLens device. You perform all of the following activities on the AWS DeepLens console using your browser, open the AWS DeepLens console at https://console.aws.amazon.com/deeplens. AWS Lambda function renders bounding boxes around detected objects (with ≥25% confidence by default) and sends JSON-formatted messages with detected object types and corresponding confidence levels to an AWS IoT MQTT topic. For a walkthrough...Creating and Deploying an AWS DeepLens Sample Project | GitHub
Extending the Object Detection project: You will capture the events from your AWS DeepLens model and put them in a queue ready for further processing; then extend the models utilizing AWS Lambda functions.
SSH to DeepLens
