PyTorch Fundamentals

Test your understanding of tensors,autograd,and model building.

1. What is the basic building block of data in PyTorch?

Array Tensor Matrix Vector

2. Which PyTorch function creates a tensor with values sampled from a standard normal distribution (mean=0, variance=1)?

torch.rand torch.zeros torch.randn torch.ones

3. Which method is used to enable gradient computation for a tensor?

.requires_grad_() .grad() .backward() .detach()

4. What is the default data type of a tensor created with torch.tensor([1, 2, 3])?

torch.float32 torch.int64 torch.int32 torch.bool

5. By default, where are PyTorch tensors stored?

GPU TPU CPU MPS

6. What does the torch.cat function do?

Splits a tensor into chunks Concatenates tensors along a specified dimension Stacks tensors along a new dimension Transposes tensor dimensions

7. Which PyTorch module provides tools for building neural networks?

torch.autograd torch.optim torch.nn torch.utils.data

8. What is the shape of the tensor created by torch.rand(3, 4, 2)?

(3, 4) (4, 2) (3, 4, 2) (2, 3, 4)

9. Which method prevents a tensor from tracking gradients?

.detach() .backward() .requires_grad_() .grad.zero_()

10. What is the result of torch.ones(2, 2) * 3?

A tensor with all elements 3 A tensor with all elements 1 A tensor with shape (3, 3) An error

11. Which of the following are valid ways to create a tensor with ones in PyTorch?

torch.ones(3) torch.ones_like(torch.zeros(2,2)) torch.full((2,2), 1) torch.empty(3).fill_(1)

12. Which operations are element-wise in PyTorch?

tensor1 + tensor2 tensor1 @ tensor2 tensor1 * tensor2 torch.matmul(tensor1, tensor2)

13. Which are components of a PyTorch training loop?

Forward pass Loss computation Backward pass Parameter update

14. Which data types are supported by PyTorch tensors?

torch.float32 torch.int64 torch.bool torch.string

15. PyTorch's autograd automatically computes gradients for tensor operations.

True False

16. Tensors must be on GPU to use autograd.

True False

17. torch.Tensor is an alias for torch.FloatTensor.

True False

18. What does 'Py' in PyTorch stand for?

19. Name the PyTorch module for optimization (abbrev.)

20. Output of torch.tensor([2, 3]) + torch.tensor([4, 5])?

Answered 0 of 0 — 0 correct

Company