AWS DeepLens – Deep learning enabled video camera for developers
1–10 of 49 posts
Re: AWS DeepLens – Deep learning enabled video camera for developers
#2100 GFLOPS can process deep learning predictions on HD video in real time? I thought even GPUs like the GTX 1080 (8.8 TFLOPS) had difficulty with that.
Re: AWS DeepLens – Deep learning enabled video camera for developers
#3"HOT DOG NOT HOT DOG" really makes it useful for adult film industry :D
Re: AWS DeepLens – Deep learning enabled video camera for developers
#4This is neat but sort of strange - I love the idea of a hardware package that makes fiddling with deep learning easy, but I wonder why Amazon went through the trouble of producing such a relatively niche product?
If I had to guess, this is going to be a great "user education" tool for AWS, designed to get new developers on the platform as early in the learning process as possible.
Re: AWS DeepLens – Deep learning enabled video camera for developers
#5"HOT DOG NOT HOT DOG" really makes it useful for adult film industry :D
I think it's rather a Silicon Valley reference.
Re: AWS DeepLens – Deep learning enabled video camera for developers
#6They don't specify what this has to enable deep learning. Intel GPU? Atom processor?
Re: AWS DeepLens – Deep learning enabled video camera for developers
#7100 GFLOPS can process deep learning predictions on HD video in real time? I thought even GPUs like the GTX 1080 (8.8 TFLOPS) had difficulty with that.
It's not very much. 100 GFLOPs is about 1-2 Haswell/Broadwell cores (32 FLOP/s * ~2 GHz AVX frequency). Even 2015 era mobile GPUs like the Apple A9 GPU (iPhone 6S) is higher throughput (~150-200GFLOP/s achievable).
If you're executing these models at 30FPS on an HD stream (say ~1mm pixels/frame), you have roughly a 100 * 10^9 / (30 * 10^6 ) = 3,000 flops/pixel budget if you're operating at peak, which is about the same flops/pixel of a 16 channel -> 16 channel 3x3 conv. In practice of course you can usually operate on a much smaller spatial input.
Re: AWS DeepLens – Deep learning enabled video camera for developers
#8Not really sure why you would use this over an Android/iOS phone and Tensorflow Mobile, or Jetson TX1+camera if you need more FLOPS at a small size
Re: AWS DeepLens – Deep learning enabled video camera for developers
#9100 GFLOPS can process deep learning predictions on HD video in real time? I thought even GPUs like the GTX 1080 (8.8 TFLOPS) had difficulty with that.
With customized model u can do that. Models like MobileNet/SqueezeNet are designed specifically for fast inference on constrained device. Although during inference, the precision of your model can be quantized as low as single digit bits. This is an active area of research, but a lot of exciting stuff is happening and the progress made is massive.
Re: AWS DeepLens – Deep learning enabled video camera for developers
#10This is great for my chicken coop project :) I have been working with a raspberry pi and camera to train a system to recognize and respond to squirrels (close the feeder to stop them eating food). There are many other options to build this, but it is nice that this is an integrated system that is easy to train!