https://drentin.au/posts/Recent content in Posts on Drentin's FindingsHugoen-usSun, 05 Feb 2023 09:00:00 +1100https://drentin.au/posts/reinvent-2022-codewhisperer/Sun, 05 Feb 2023 09:00:00 +1100https://drentin.au/posts/reinvent-2022-codewhisperer/A hands-on session at AWS re:Invent put CodeWhisperer to the test. Here’s what an AI coding companion could do, where it fell short, and why understanding your own code still matters.https://drentin.au/posts/is-it-a-yes/Fri, 24 Sep 2021 01:00:00 +1000https://drentin.au/posts/is-it-a-yes/<p>Starting last week I felt like I was ready to jump into attempting to work off the knowledge I had built up doing the examples previously and attempt the main goal: to create a model that was capable of recognising some of the Japanese Hiragana character set.</p> <h1 id="problem---input-data">Problem - Input Data!</h1> <p>My initial problem that I had been playing with was the idea of a training data set - where would I get a good set of training data from?</p>https://drentin.au/posts/compost-landfill-recycling/Wed, 15 Sep 2021 01:00:00 +1000https://drentin.au/posts/compost-landfill-recycling/<h1 id="what-we-all-came-here-for-sagemaker">What we all came here for&hellip; SageMaker!</h1> <p>I was excited to get stuck into <a href="https://www.awsdeeplens.recipes/400_advanced/410_trash_sorter/">the Advanced recipe - Build a custom ML model to sort trash</a> as this started getting into the parts I wanted to know more about; how to get a basic model trained in SageMaker and then deploy it to the DeepLens device.</p> <h1 id="step-1---train">Step 1 - Train!</h1> <p>Luckily in this example they include a number of sample images, quite a decent set really with over 500 images in total, separated into Compost, Landfill and Recycling.</p>https://drentin.au/posts/first-figure-out-how-to-do/Mon, 13 Sep 2021 23:29:11 +1000https://drentin.au/posts/first-figure-out-how-to-do/<h1 id="beginnings-start-here">Beginnings start here!</h1> <p>Hello all and welcome to my first article around my attempts to create an Amazon SageMaker-based solution, focusing on image detection.</p> <p>I am participating in an initiative as part of my company&rsquo;s AWS Community of Practice. The idea is inspired loosely by <a href="https://acloudguru.com/blog/engineering/how-to-build-a-netflix-style-recommendation-engine-with-amazon-sagemaker">A Cloud Guru&rsquo;s How to Build a Netflix Style Recommendation Engine with Amazon SageMaker Challenge</a> and I have got my hands on an AWS DeepLens so I&rsquo;m going to see what I can do with both of these to the best of my ability!</p>