Gabriele
@gabiett.bsky.social
Innovation my ❤️. I am from Austria 🇦🇹 she/her 🔬 R&D: Hygiene. Biocompatibiliy. Medical Devices
Reposted by Gabriele
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
August 27, 2025 at 1:19 AM
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
Reposted by Gabriele
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
August 22, 2025 at 12:14 PM
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
Reposted by Gabriele
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
August 18, 2025 at 12:11 PM
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
Reposted by Gabriele
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
August 17, 2025 at 12:14 AM
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
Reposted by Gabriele
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
August 15, 2025 at 11:54 PM
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
Reposted by Gabriele
My absolutely most hated Error when using python. Similar to C's Segmentation fault (core dumped).
August 11, 2025 at 1:19 PM
My absolutely most hated Error when using python. Similar to C's Segmentation fault (core dumped).
Reposted by Gabriele
Day 52: Turns out my loss term wasn't differentiable. Thanks goes out to my amazing PhD team for spotting it! #100DaysOfCode
August 11, 2025 at 1:16 PM
Day 52: Turns out my loss term wasn't differentiable. Thanks goes out to my amazing PhD team for spotting it! #100DaysOfCode
Reposted by Gabriele
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
August 13, 2025 at 8:16 PM
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
Reposted by Gabriele
Day 51: Looking at my neural network layers with deep dream! #100DaysOfCode
July 31, 2025 at 1:03 PM
Day 51: Looking at my neural network layers with deep dream! #100DaysOfCode
Reposted by Gabriele
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
July 25, 2025 at 1:33 PM
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
Reposted by Gabriele
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
July 23, 2025 at 8:47 AM
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
Reposted by Gabriele
Day 48: Optimisation of graph visualisation in 3D!! (currently not working) #100DaysOfCode
July 22, 2025 at 10:03 PM
Day 48: Optimisation of graph visualisation in 3D!! (currently not working) #100DaysOfCode
Reposted by Gabriele
Day 47: Doing some optimisation. It's working! at least in a small scale! #100DaysOfCode
July 7, 2025 at 7:15 PM
Day 47: Doing some optimisation. It's working! at least in a small scale! #100DaysOfCode
Reposted by Gabriele
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
June 29, 2025 at 3:57 PM
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
Reposted by Gabriele
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
June 17, 2025 at 12:27 PM
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
Reposted by Gabriele
Day 44: Plotting data for genes related to AMD. Super excited to feed a neutral network with it combined with images 😍 #100DaysOfCode
May 27, 2025 at 11:14 PM
Day 44: Plotting data for genes related to AMD. Super excited to feed a neutral network with it combined with images 😍 #100DaysOfCode
Reposted by Gabriele
Day 42: Yesterday I was trying to implement a dataloader and for whatever magic reason it's not working. #100DaysOfCode
April 26, 2025 at 1:27 AM
Day 42: Yesterday I was trying to implement a dataloader and for whatever magic reason it's not working. #100DaysOfCode
Reposted by Gabriele
Day 42: Suddenly everything stopped working ... #100DaysOfCode
May 7, 2025 at 4:39 PM
Day 42: Suddenly everything stopped working ... #100DaysOfCode
Reposted by Gabriele
Day 43: Music to my ears (or to my laptops ears) - new cuda version after 4 years! #100DaysOfCode
May 8, 2025 at 11:39 AM
Day 43: Music to my ears (or to my laptops ears) - new cuda version after 4 years! #100DaysOfCode
Reposted by Gabriele
Day 31: Searching for some benchmarking datasets and metrics! #100DaysOfCode
February 23, 2025 at 5:32 PM
Day 31: Searching for some benchmarking datasets and metrics! #100DaysOfCode
Reposted by Gabriele
Day 32: I promise, I am an expert in deep learning. #100DaysOfCode
February 24, 2025 at 2:59 AM
Day 32: I promise, I am an expert in deep learning. #100DaysOfCode
Reposted by Gabriele
Day 33: Clearly not working. Still, I made progress with understanding LSTM. #100DaysOfCode
February 27, 2025 at 4:49 AM
Day 33: Clearly not working. Still, I made progress with understanding LSTM. #100DaysOfCode
Reposted by Gabriele
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
March 3, 2025 at 8:03 AM
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
Reposted by Gabriele
Day 35: Lots of modularity and honey bee colony loss write-up! #100DaysOfCode
March 8, 2025 at 5:31 AM
Day 35: Lots of modularity and honey bee colony loss write-up! #100DaysOfCode