So this is a quick note about something interesting I’ve come across. I own a Machine Learning Software-as-a-Service called Product Pix which I lovingly built as a side hustle. I wrote about it in the past if you’re curious. It’s a neat little service where you upload a photo, and get its background removed. Like so:
Anyway! The business is doing nicely. And along stripe comes and offers me a loan. Take 4000$, and pay back 4500$. We’ll deduct your sales at a rate of 16.8% of your sales cycle.
My first payment from a real customer finally cleared. Product Pix just made $65.36. I feel like I can finally write a bit about my journey so far in building a SaaS (software as a service). I can finally tell for sure that someone out there thinks my site is generating real value.
And the site still doesn’t have any payment or subscription page! The transaction arose from the client reaching out to me and asking how much the service costs, because they needed to use my service at scale.
That’s a good sign, right? So elegant. Here I am, a machine learning consultant, writing some code on my spare time, and I’m getting people to pay me for using it. Sheer elegance. …
In one of his books, Isaac Asimov envisions a future where computers have become so intelligent and powerful, that they are able to answer any question. In that future, Asimov postulates, scientists don’t become unnecessary. Instead, they’re left with a difficult task: figuring out how to ask the computers the right questions: those that yield an insightful, useful answer.
We’re not quite there yet, but in some sense we are.
In times of old, it used to be the case that a lot of the effort in machine learning went into the implementation of its mechanics. With the advent of popular machine learning frameworks such as Tensorflow, Pytorch and the like, we can happily shrug away that burden. The mechanics of tweaking a model’s weights to achieve a certain goal is abstracted away. Defining a custom optimization goal is as easy as writing it down, and your favorite deep learning framework chugs away and minimizes the error (or loss) accordingly. …
Tensorflow is great. Really, you can do everything imaginable. You can build really cool products with it. However, Tensorflow’s code examples generally tend to gloss over how to get data into your model: they either sometimes naively assume that someone else did the hard work for you and serialized the data into Tensorflow’s native format, or showcase unreasonably slow methods that would have a GPU idling away with shockingly low performance. Also oftentimes the code is very hacky and difficult to follow. …