In this blog post series, we will look at a simple example of modeling an IoT device process as a workflow, using primarily AWS IoT and AWS Step Functions. Our example is a system where, when a device comes online, you need to get external settings based on the profile of the user the device belongs to and push that configuration to the device. The system that holds the external settings is often a third party... - Source: dev.to / about 1 year ago

Iot - MQTT broker to send messages to the Raspberry Pi. - Source: dev.to / over 2 years ago

" Amazon Web Services offers a broad set of global cloud-based products including compute, storage, databases, analytics, networking, mobile, developer tools, management tools, IoT, security and enterprise applications. These services help organizations move faster, lower IT costs, and scale. AWS is trusted by the largest enterprises and the hottest start-ups to power a wide variety of workloads including: web and... Source: over 2 years ago

AWS IoT Core - message broker between all devices and AWS. - Source: dev.to / over 2 years ago

If you have to ask, then you should be using AWS by default. They have plenty of IoT services for you to fiddle around with and get started. Source: almost 3 years ago

According to https://cloud.google.com/tpu, each individual TPUv3 has 420 Teraflops, and TPUv4 is supposed to double that performance, so if that guess is correct, it should take a few seconds to do inference. Quite impressive really. - Source: Hacker News / about 2 years ago

You can also rent a cloud TPU-v4 pod (https://cloud.google.com/tpu) which 4096 TPUv-4 chips with fast interconnect, amounting to around 1.1 exaflops of compute. It won't be cheap though (excess of 20M$/year I believe). - Source: Hacker News / over 2 years ago

Actually, that's done with TPUs which are more efficient: https://cloud.google.com/tpu. Source: almost 3 years ago

TPU training uses Google silicon and is thus a true deep learning alternative to Nvidia. Source: almost 3 years ago

The server choice really depends on how much CPU and RAM the requests take, how many users will be hitting the server, etc. You can start with a $5/month Digital Ocean server (or AWS or Google) and see if that works for you. Or you can outsource the server administration to Amazon or Google if you don't want to deal with it or need specialized tpu hardware. Source: about 3 years ago