Backup of The Bitter Lesson
Some time ago “The Bitter Lesson” web page went down for some reasons. This is a verbatim copy of this valuable lesson for all ML community.
Here is a collection of my hobbies, some tests, small projects, failed experiments and some successful ones, too!
And remember! “If things are not failing, you are not innovating enough.“ [Elon Musk]
Check out my GitHub repos for some small contributions to the FOSS world.
Let’s connect!
Have a question? Or need help with a similar problem? Find me on your favourite channel!
Conda alternative to installing PyTorch 2.5.1
In a recent tweet, Pytorch announced that they will no longer publish packages to Anaconda.
Below is an alternative that works, for now.
Make your data scientists and DevOps happy with one Tilebox
Organizations adopting Tilebox find their scientists focused on algorithms while their infrastructure teams efficiently manage resources and costs. How is this possible?
LLM success? Keep the data flywheel spinning!
LLMs are quite powerful and can solve a wide range of problems! Employing them is easy but assessing their performance in production is still a hard problem.
An overconfident model can ruin your business faster than a low performer.
Read on for an approach. Live demo!!!
Boost Your Models: Insights in data and label augmentation in torchvision
Data augmentation is a technique used to increase the diversity of data available for training models. Until recently, managing both mask and bounding box augmentations simultaneously with the same parameters was challenging in torchvision. Starting with v0.15 torchvision added more streamlined and flexible augmentation capabilities that are easier to use and more consistent with the…
Mask R-CNN: A cornerstone architecture for Computer Vision. Explore a detailed schema showing its intricate components.
Take a closer look at the step-by-step breakdown of Mask R-CNN to make it easier to understand how it works. This guide will help you navigate its implementation in torchvision, making the complex process more accessible and straightforward.