Ml

One of the features of our smart home is when the doorbell on our house is rung or a letter is posted, a snapshot is taken by a security camera pointed to our front door. The snapshot is then sent to a neural network to identify if it’s the post or not. If it is then house will announce this to us, which is handy to decide if it’s worth getting up from the sofa to pick up letters / answer the door. [Read More]

Scikit-learn is a great python library for all sorts of machine learning algorithms, and really well documented for the model development side of things. But once you have a trained classifier and are ready to run it in production, how do you go about doing this? There’s a few managed services that will do it for you, but for my situation these weren’t a good fit. We just wanted to deploy the model onto a modest sized Digital Ocean instance, as a REST API that can be externally queried. [Read More]