Day 64: Variational autoencoder session - trying to disentangle the latent variables (supervised version). PLEASE WORK. #100DaysOfCode

Day 65: Yesterday I did some coding on paper to understand how to design my next experiment! #100DaysOfCode

Day n: Why was 6 scared of 7? CAUSE SEVEN ATE NINE!!! Working on latent spaces in autoencoders. Fun. #100DaysOfCode

I don't know which day, but I am sharing the things that don't work at 2am, and haven't worked for the past two days (or ever) 😂 #100DaysOfCode

Bregenz

Day 57: Classic moment of "It works and nobody knows why". The training of my model should break when there is no connection between green and yellow filters. Well, it doesn't. #100DaysOfCode

Day 56: Doctorate meeting went well - taked about a multi-objective loss. Prof said, if the project was a funnel, we are at the red arrorw. I think that's something positive! Also, for the next "sprint": two P's - Passion and a little bit of Panic! #100DaysOfCode

Day 55: OMG, I did it, the loss function doesn't throw any errors anymore. Differentiable now, understood how .to(device) is handled in lightning and learned more about gradients and how graphs are computed. #100DaysOfCode

Day 54: Today, I realised that I overcomplicated my whole loss function. Instead of just looping through the paramerters saved in the model, I am crawling through the network. At least I know it now and can fix the mess! 🤩 #100DaysOfCode

My absolutely most hated Error when using python. Similar to C's Segmentation fault (core dumped).

Day 52: Turns out my loss term wasn't differentiable. Thanks goes out to my amazing PhD team for spotting it! #100DaysOfCode

Day 53: Fundus images didn't work, so I will get into enface OCT - using some slabs. Hence, I will get into layer segmentation next!! #100DaysOfCode

Day 51: Looking at my neural network layers with deep dream! #100DaysOfCode

Love your journey!

Day 50: Dataloader for Kandinsky patterns is done! Now I need to find a loss term that makes my network not only sparse but also modular! So in love with my PhD team, they help me verbalise my problems 🤓 #100DaysOfCode

Day 49: Meeting with my Doctoral supervisor and advisors was fun as always! Great new ideas for how to proceed - mainly dataset and loss term related. #100DaysOfCode

Day 48: Optimisation of graph visualisation in 3D!! (currently not working) #100DaysOfCode

Day 47: Doing some optimisation. It's working! at least in a small scale! #100DaysOfCode

Day 46: Goal to get all of the umap plots look similar: failed. Tried with transform once, fit multiple times. Maybe the amount of datapoints is the problem. Keep going, keep growing! #100DaysOfCode

Day 45: Yesterday, I tried to further understand my data. The labels don't make too much sense to me, hence messaged a clinician! #100DaysOfCode

Day 44: Plotting data for genes related to AMD. Super excited to feed a neutral network with it combined with images 😍 #100DaysOfCode

Day 42: Yesterday I was trying to implement a dataloader and for whatever magic reason it's not working. #100DaysOfCode

Day 42: Suddenly everything stopped working ... #100DaysOfCode

Day 43: Music to my ears (or to my laptops ears) - new cuda version after 4 years! #100DaysOfCode

Day 31: Searching for some benchmarking datasets and metrics! #100DaysOfCode

Error messages and way too high loss values.

Day 32: I promise, I am an expert in deep learning. #100DaysOfCode

Python/Matplotlib, showing (bad) prediction results.

Day 33: Clearly not working. Still, I made progress with understanding LSTM. #100DaysOfCode

Day 34: Made progress on my code today thanks to @mateosuffern.bsky.social! Turning some pytorch code into pytorch lightning. My favourite part are the sanity checks! #100DaysOfCode

Day 35: Lots of modularity and honey bee colony loss write-up! #100DaysOfCode

and the actual update - trying to translate pytorch into torch lightning!