I hate these questions

PanNuke is a flawed dataset and having a good score on it actually a bad thing? For example, left image is an example from the dataset, the middle is ground truth and right is my model's prediction. According to a doctor friend my model is right and GT is wrong. How can a model learn from this?

I will give a training about ML on the GCP in 5 mins 🎤

Hey everyone, once again I proved that I'm a pro about GCP and ML *mic drop* hehe😁 This certificate basically means I know my way around GCP when a business problem needs to be solved using machine learning on the Google Cloud!

It turns out you have to do that to have a better bluesky experience

Choose your fighter👇 Additional information:

- All models are for the same task
- There is also a training py for all but I forget to add
- All models needs to use a dataset . py and maybe other scripts, so think about where to put it and how it would change the structure

Me: Professional Google Certified Superhero Machine Learning MLOps Engineer

My Model:

When I cluster the features from the UNI model,
2 clusters: Foreground background
3 clusters: Border information added
4 clusters: Parts where the model isn't sure if it is a border or background added

Now I need to find an original way to use this information for designing a segmentation decoder

Yeap found it 😄

I think I saw a post about how it switch to Chinese when it "really" needs to thinks. And people were referring to Karpathy's tweet below

I have a question. For example, first sentence in the introduction sections contains 5 references. Is that really necessary or is it there to show that authors made their homework and read them?

Design and finding the most original (!) ideas are my passion 😂

The model's image representation is very strong for segmentation but attention visualization of the CLS token cannot show you the objects in the image like DINO V2 trained on ImageNet. Funny fact: This model's CLS token also attends to the bird if you give an image of a bird 😂

Attention visualization of a selected patch in the selected layers of a model. I used UNI (A General-Purpose Self-Supervised Model for Computational Pathology), which uses DINOV2 method, for the screenshot below.