This step-by-step tutorial will guide you through creating and deploying your first deep learning model with AWS DeepLens. AWS DeepLens is a programmable video camera designed to expand deep learning development skills. It comes with tutorials, code, and pre-trained models. In this tutorial, you will create a project, then deploy and view the project output directly from the device
You will need an AWS DeepLens device in order to complete this tutorial. You can pre-order now on amazon.com.
If you want to view the project output on a monitor you will also need: USB keyboard, USB mouse, monitor with Micro HDMI cable and a USB hub.
If this is your first time using your AWS DeepLens, start with the Configure Your New AWS DeepLens tutorial or if you're looking to do more with your device take a look at the Extending Your AWS DeepLens Project tutorial.
Open the AWS Management Console in a new browser window, so you can keep this step-by-step guide open. When the screen loads, enter your user name and password to get started. Then type DeepLens in the search bar and select AWS DeepLens to open the console.
a. The console should open on the Projects screen where you'll see an empty project list, select Create new project on the top right (if you don’t see the project list view, click on the hamburger menu on the left and select Projects)
b. Choose, Use a project template as the Project type, and select Object detection from the project templates list.
Scroll down the screen and select Next.
c. Accept the default values in the Project name and Description fields.
d. On the Project Content sceen, accept the default values for the Model and the Function, and select Create.
a. Verify that the project was created successfully, and select it from the list to start the deployment flow.
b. Choose the radio button for the project and select Deploy to device.
c. On the Target device screen, choose your device from the list, and select Review.
d. Now it's time to review the details of the deployment and select Deploy.
e. On the AWS DeepLens console, you can track the progress of the deployment. It can take a few minutes to transfer a large model file to the device.
a. Select, View project stream on the MyDevice page.
b. Follow the step-by-step instructions provided in the console, including entering the command: mplayer -demuxer lavf -lavfdopts format=mjpeg:probesize=32 /tmp/results.mjpeg to start a media player and watch your project's video stream.
c. You should now see the output from AWS DeepLens on the moitor. You're all set to go start detecting objects! Get started by pointing the AWS DeepLens at your laptop or water bottle to see what happens.