As a child, the Nintendo DS awoke something in me. It was the single greatest piece of technology I had ever owned up to that point (and probably ever will be, to be perfectly honest). I once played it for so long in a single sitting that my hands actually turned blue. Suffice it to say, I loved my Nintendo DS. And of all the games on the console, I played Super Mario 64 DS the most. And of all the minigames on Super Mario 64 DS, I played “Wanted!” the most.
Two weeks ago, I watched a YouTube video of someone revisiting the game in 2022 and playing through the different minigames offered, and was reminded of “Wanted!” again, over 10 years later. As I watched the video, the wheels began to turn in my brain.
After so long of feeling burnt out as a data scientist, I finally felt inspired again!
I know this is not exactly the most technically challenging side project in the world, but I feel like the best thing to do for me in this situation is to value a project that gets me excited to code over one that is potentially more impressive. And at the end of this work, two weeks later, I can confidently say I had fun working on it 🙂
I’ve published this blog post on Medium, but I’ve disabled ads on the article, so you should be able to read it on there for free.
Letting an object detection model control a DS emulator to become an expert in playing the Super Mario 64 DS minigame, “Wanted!”
All the code used for this project is on my GitHub.