Skip to content
ml-recall

#align-corners

1 question from Segmentation

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

hardAI-checkedSegmentation

A two-pixel signal is upsampled by linear interpolation:

import torch
import torch.nn.functional as F

x = torch.tensor([[[0.0, 10.0]]])          # shape (1, 1, 2)
a = F.interpolate(x, scale_factor=2, mode="linear", align_corners=False)
b = F.interpolate(x, scale_factor=2, mode="linear", align_corners=True)

Both outputs have 4 values. The second value of a is and the second value of b is .

Fill in every blank (hints in the boxes). Enter moves to the next blank.