Posted On: Jun 14, 2018
Today, we are excited to announce some important new capabilities for AWS DeepLens in addition to the ability to buy now on amazon.com.
Expanded Framework Support – DeepLens is now optimized for the TensorFlow and Caffe frameworks. You can find the models and modeling layers that AWS DeepLens supports for each framework in the supporting AWS documentation for this feature.
Expanded MXNet Layer Support – DeepLens now supports the Deconvolution, L2Normalization, and LRN layers provided by MXNet. For more information see the supporting AWS documentation for this feature.
Kinesis Video Streams – The video stream from the DeepLens camera can now be used in conjunction with Amazon Kinesis Video Streams. You can stream the raw camera feed to the cloud and then use Amazon Rekognition Video to extract objects, faces, and content from the video. You can also build custom applications using popular open-source ML frameworks to process and analyze your video streams. For more information see the supporting AWS documentation for this feature.
New Sample Project – DeepLens now includes a sample project for head pose detection. This sample project uses a deep learning model generated with the TensorFlow framework to accurately detect the orientation of a person’s head. You can examine this sample to see how the model was constructed. For more information see the supporting AWS documentation for this feature.
In addition to the feature updates, you can now view the output of your projects over a browser while on the same network. For more information see the supporting AWS documentation for this feature.
You can learn more about AWS DeepLens and order your device by visiting the AWS DeepLens website. For other useful resources including video tutorials and developer guide visit the DeepLens resources page. You can also subscribe to the DeepLens discussion forum to get new launch announcements and post your questions.