2022-02-05
#python
#machine-learning
#conference
#SFI 2022 As mentioned earlier, I will be giving a talk on the 17th SFI IT Academic Festival on the topic of style transfer and StyleGAN. In this post I would like to show you how easy it is to play with style transfer on your own!
To tutorial or not to tutorial # It might be obvious for you to check Tensorflow/PyTorch tutorials if you wanted to learn how to create style-transfer system.
2022-01-20
#conference
#SFI 2022
#machine-learning I am happy to share that I was invited (for the first time in my life!) to give a talk on a conference. ๐ It will be the 17th SFI IT Academic Festival, organized by students from the Jagiellonian University in Cracow. The conference will be held on 14-16 of March 2022.
My lecture will be in Polish on topic StyleGAN w Twoich rฤkach -> StyleGAN in Your Hands, I will talk about transfer learning in general and later about StyleGANv2.
2022-01-14
#machine-learning
#streamlit
#python
#appsilon This one is short. :)
Usually when we are doing ML experiments, training models, preparing EDA, we want to share the results with the World at some point. One of the quickest and easiest ways to do so in python, to create a simple webapp with results, is a super-cool library streamlit! If you thought building an app in flask is easy, you will be amazed by streamlit simplicity. Actually you do not have to create an ML related app, nobody checks that ;).
2022-01-04
#math
#programing
#julia
#aoc2021 This year I took part in the advent of code event. If you’ve never heard about it, I attach tl;dr bellow. Today, I’d like to share my solution for Day 7 problem, because I find it very interesting.
In the first half of the post I describe comparison in time complexity of two solutions (programming). In the second half I outline the proof of one solution (math). What is the Advent of Code # For sure you had some kind of advent calendar in the past (or you still have), e.
2021-11-29
#machine-learning
#python
#appsilon As mentioned a month ago, I write a series of posts on detecting solar panels from satellite images at my company, Appsilon.
In this post I focus on using fastai python library to deliver a working ML model in few hours!
2021-11-26
#math
#circles
#pizza Today I have a short one, a follow-up to the post on pizza sizes. Recently, I was in my local pizza place where I had to choose between 32 and 46cm pizza. The bigger one cost 5 PLN more. Even without looking at my table, I chose the bigger one. I knew, however, that I’m going to eat only half of my pizza so I asked to pack the remaining half.
2021-11-21
#math
#optimization
#julia In the previous post I’ve presented the basics of stating mathematical optimization problems and JuMP framework in julia.
Today let’s follow up with concrete examples!
Please checkout the accompanying jupyter notebook even though you might not feel like a programmer.
It’s very clear and shows how easy it is to obtain solutions!
2021-11-07
#math
#optimization
#julia In the post about fitting pizzas inside another pizza I’ve shown the following picture and promised a post about recreating it.
Pizzas packed in pizza However, I would not like to assume that everyone is familiar with the optimization theory (you may graduate from Computer Science and still not know a lot) so I want to present an introduction here as high school math and quadratic equations are enough to understand those concepts.
2021-11-02
#machine-learning
#python
#appsilon I’m writing a series of posts on detecting solar panels from satellite images at my company, Appsilon.
To be honest, not from satellite images but from orthophotos.
If you don’t know what are orthophotos, the good news is that the first post has been released recently!.
2021-10-16
#performance
#summing
#julia In a recent post, I presented how memory layout may influence a matrix summing speed.
It’s interesting to see that there are plenty of pitfalls we might fall into when writing sum function and memory layout is not the only one.
Please first read the previous post on summing if you haven’t already.
Without thinking why, let’s take a look at those two functions: