Skip to content
← All tracks

Orientation and the Grade

PyTorch

What "graded" means here, before any PyTorch is taught. A solution that returns exactly the right numbers and still fails, because it copied a buffer it could have viewed. The rule is learned once rather than resented later.

0 / 3 solved
Continue →
  1. 1. Not solved yet. Three passes, or two
  2. 2. Not solved yet. The right answer, the wrong cost
  3. 3. Not solved yet. The bug that only shows on a square

Check yourself

4 questions · one attempt each

These do not count toward finishing the track. They are here to catch the things that are easy to read past.

0 / 4

What is the shape of torch.tensor(3.0), and what does .item() give? 

t = torch.tensor(3.0)
t.shape
t.item()
Question 1 of 4