working gallery, working skills
This commit is contained in:
parent
9e63f46919
commit
793f028a40
304 changed files with 3751 additions and 200 deletions
|
|
@ -1,78 +0,0 @@
|
|||
+++
|
||||
title = "Coding Examples"
|
||||
date = 2022-03-01
|
||||
authors = ["Aron Petau"]
|
||||
description = "A selection of coding projects from my Bachelor's in Cognitive Science"
|
||||
|
||||
gallery:
|
||||
- url: /assets/images/sample_lr.png
|
||||
image_path: /assets/images/sample_lr.png
|
||||
title: "A low-resolution sample"
|
||||
- url: /assets/images/sample_hr.png
|
||||
image_path: /assets/images/sample_hr.png
|
||||
alt: ""
|
||||
title: "A high-resolution sample. This is also called 'ground truth' "
|
||||
- url: /assets/images/sample_sr.png
|
||||
image_path: /assets/images/sample_sr.png
|
||||
alt: " "
|
||||
title: "The artificially enlarged image patch resulting from the algorithm"
|
||||
- url: /assets/images/sample_loss.png
|
||||
image_path: /assets/images/sample_loss.png
|
||||
alt: ""
|
||||
title: "A graph showing an exemplary loss function applied during training"
|
||||
- url: /assets/images/sample_cos_sim.png
|
||||
image_path: /assets/images/sample_cos_sim.png
|
||||
alt: ""
|
||||
title: "One qualitative measurement we used was pixel-wise cosine similarity. It is used to measure how similar the output and the ground truth images are"
|
||||
|
||||
[taxonomies]
|
||||
tags = [
|
||||
"AI",
|
||||
"CNN",
|
||||
"GOFAI",
|
||||
"MTCNN",
|
||||
"computer vision",
|
||||
"ethics",
|
||||
"face detection",
|
||||
"google colab",
|
||||
"jupyter notebook",
|
||||
"keras",
|
||||
"machine learning",
|
||||
"neural nets",
|
||||
"object recognition",
|
||||
"python",
|
||||
"super resolution",
|
||||
"tensorflow",
|
||||
"university of osnabrück"
|
||||
]
|
||||
|
||||
[extra]
|
||||
banner = "/images/sample_lr.png"
|
||||
show_copyright = true
|
||||
show_shares = true
|
||||
+++
|
||||
|
||||
## Neural Networks and Computer Vision
|
||||
|
||||
## A selection of coding projects
|
||||
|
||||
Although pure coding and debugging are often not a passion of mine, I recognize the importance of neural networks and other recent developments in Computer Vision. From several projects regarding AI and Machine Learning that I co-authored during my Bachelor Program, I picked this one since I think it is well documented and explains on a step-by-step basis what we do there.
|
||||
|
||||
### Image Super-Resolution using Convolutional Neural Networks (Recreation of a 2016 Paper)
|
||||
|
||||
Image Super-Resolution is a hugely important topic in Computer Vision. If it works sufficiently advanced, we could take all our screenshots and selfies and cat pictures from the 2006 facebook-era and even from before and scale them up to suit modern 4K needs.
|
||||
|
||||
Just to give an example of what is possible in 2020, just 4 years after the paper here, have a look at this video from 1902:
|
||||
{% include video id="EQs5VxNPhzk" provider="youtube" %}
|
||||
|
||||
The 2016 paper we had a look at is much more modest: it tries to upscale only a single Image, but historically, it was one of the first to achieve computing times sufficiently small to make such realtime-video-upscaling as visible in the Video (from 2020) or of the likes that Nvidia uses nowadays to upscale Videogames.
|
||||
|
||||
{% include gallery caption="Example of a Super-Resolution Image. The Neural network is artificially adding Pixels so that we can finally put our measly selfie on a billboard poster and not be appalled by our deformed-and-pixelated-through-technology face." %}
|
||||
|
||||
[The Python notebook for Image super-resolution in Colab]( https://colab.research.google.com/drive/1RlgIKJmX8Omz9CTktX7cdIV_BwarUFpv?usp=sharing){: .btn .btn--large}
|
||||
|
||||
### MTCNN (Application and Comparison of a 2016 Paper)
|
||||
|
||||
Here, you can also have a look at another, much smaller project, where we rebuilt a rather classical Machine learning approach for face detection. Here, we use preexisting libraries to demonstrate the difference in efficacy of approaches, showing that Multi-task Cascaded Convolutional Networks (MTCNN) was one of the best-performing approaches in 2016. Since I invested much more love and work into the above project, I would prefer for you to check that one out, in case two projects are too much.
|
||||
|
||||
[Face detection using a classical AI Approach (Recreation of a 2016 Paper)](https://colab.research.google.com/drive/1uNGsVZ0Q42JRNa3BuI4W-JNJHaXD26bu?usp=sharing){: .btn .btn--large}
|
||||
|
|
@ -1,68 +0,0 @@
|
|||
+++
|
||||
title = "Homebrew"
|
||||
date = 2022-03-01
|
||||
authors = ["Aron Petau"]
|
||||
description = "A bubbly hobby of mine"
|
||||
|
||||
[taxonomies]
|
||||
tags = [
|
||||
"altbier",
|
||||
"beer",
|
||||
"experiment",
|
||||
"fermentation",
|
||||
"hops",
|
||||
"homebrew",
|
||||
"keg",
|
||||
"lager",
|
||||
"pressure",
|
||||
"private",
|
||||
"sustainability",
|
||||
"yeast"
|
||||
]
|
||||
|
||||
gallery:
|
||||
- url: /assets/images/beer_setup.jpg
|
||||
image_path: /assets/images/beer_setup.jpg
|
||||
title: "The latest iteration of my homebrew setup, using pressure tanks and a pressurized fermentation chamber"
|
||||
- url: /assets/images/beer_setup_2.jpg
|
||||
image_path: /assets/images/beer_setup_2.jpg
|
||||
title: "An electric kettle I use for the Brew"
|
||||
- url: /assets/images/beer_tap.jpg
|
||||
image_path: /assets/images/beer_tap.jpg
|
||||
title: "I made my own kegging system featuring a tap from an old table leg."
|
||||
- url: /assets/images/beer_fermentation.jpg
|
||||
image_path: /assets/images/beer_fermentation.jpg
|
||||
title: "An active fermentation"
|
||||
- url: /assets/images/hops.jpg
|
||||
image_path: /assets/images/hops.jpg
|
||||
title: "Hops growing in our garden, so I can experiment with fresh specialty hops"
|
||||
- url: /assets/images/beer_malt.jpg
|
||||
image_path: /assets/images/beer_malt.jpg
|
||||
title: "The leftover mass of spent grain.
|
||||
Animals love it, it's great for composting,
|
||||
but most importantly, its great for baking bread!"
|
||||
|
||||
[extra]
|
||||
banner = "/images/beer_tap.jpg"
|
||||
show_copyright = true
|
||||
show_shares = true
|
||||
+++
|
||||
|
||||
## Brewing
|
||||
|
||||
### Making my own beer
|
||||
|
||||
I love hosting, I love experimenting in the Kitchen. Starting with homebrews was a natural fit for me and during the first wave of Covid-19, I went the whole homebrewer’s route of bottle fermentation and small batches later elevating my game with larger batches of 50 liters and a pressure tank system.
|
||||
|
||||
Starting out, I found it fascinating, how just 4 rather simple ingredients, malt, hops, water and yeast, can form such an incredible range of taste experiences. It was and still is, a tremendous learning experience, where one slowly has to accept not being able to control the process fully and find room for creativity.
|
||||
|
||||
Why do I present such an unrelated non-academic hobby here? I simply do not regard it as unrelated, experimenting and optimizing a process and a workflow, creating optimal conditions for the yeast to do its job feels very similar to approaching a coding project.
|
||||
Yeast and what it does fascinates me. Every time I open the latch to release some pressure on the Tank I think of the awesome symbiotic relationships yeast has with humans and how many different strains live there together to create a unique, yet tailored flavor. Several ideas are floating around of changing the brewing process by capturing the created carbon dioxide and using it productively. I could see a car tire being filled with my beer gas, or an algae farm munching away on my CO2 byproducts. Within a closed-loop pressurized system, such ideas actually become realizable and I would love to explore them further.
|
||||
|
||||
I am not yet an expert on algae, but I can manage with yeast and I believe they can coexist and create a more sustainable cycle of production.
|
||||
Young Henrys, a brewery in Australia is already incorporating algae into its industrial process:
|
||||
[The Algae project](https://younghenrys.com/algae){: .btn .btn--large}
|
||||
|
||||
Such ideas do not come into the industry by themselves: I believe that art and the exploratory discovery of novel techniques are the same things. Good and inventive design can improve society and make steps towards sustainability. I want to be part of that and would love to find new ways of using yeast in other design contexts: See whether I can make them work in a closed circular system, make them calculate things for me, or simply making my next beer taste awesome with just the right amount of fizz.
|
||||
|
||||
{% include gallery caption="Some selected photos of the process in our Kitchen" %}
|
||||
Loading…
Add table
Add a link
Reference in a new issue