✳flâneur — a map of the web's best reading

fasttransform: Reversible Pipelines Made Simple – fast.ai

fast.ai · 3,380 words · saved by 1 readers

Introducing fasttransform, a Python library that makes data transformations reversible and extensible through the power of multiple dispatch. “How did this image get misclassified?” If you’ve ever trained a machine learning model, you know what comes next: the frustrating journey of trying to understand what your model actually saw. You dig through layers of transformations - normalizations, resizes, augmentations - only to realize you’ll need to write inverse functions just to see your data again. It’s so painful that many of us skip it altogether, debugging our models based on abstract numbers rather than actual data. Or as OpenAI’s Greg Brockman puts it: Let’s look at what you might be missing. Here’s a simple example using fastai: With just these four lines, we discover something fascinating: our “wolf detector” isn’t detecting wolves at all - it’s detecting snow! Look at the training data: wolves in snow, huskies in forests. Then look at the predictions: the model fails whenever w

fasttransform: Reversible Pipelines Made Simple – fast.ai fasttransform: Reversible Pipelines Made Simple Introducing fasttransform, a Python library that makes data transformations reversible and extensible through the power of multiple dispatch. “How did this image get misclassified?” If you’ve ever trained a machine learning model, you know what comes next: the frustrating journey of trying to understand what your model actually saw. You dig through layers of transformations - normalizations, resizes, augmentations - only to realize you’ll need to write inverse functions just to see your da

Explore this link on the map →

saved by

related reading