Skip to content
← All PyTorch tracks

Image Pattern Lab

PyTorch

Build a tiny image classifier using contrast filters and a learned classification head.

Build · inspect · experiment

What you’ll build

  1. Extract two contrast features from each image.
  2. Train the classification head and record its loss.
  3. Inspect predictions and test shifted or low-contrast patterns.

Prerequisites: Slicing, reductions, sigmoid and gradient descent. CPU-friendly; a GPU is optional.

Try the other framework →
0 / 1 solved
Start →
  1. 1. Not solved yet. Image Pattern Lab