GPU tensors (to, cuda) in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output device of the tensor?

Consider the following PyTorch code snippet. What device will the tensor be on after execution?

PyTorch

import torch
x = torch.tensor([1, 2, 3])
x = x.to('cuda')
print(x.device)

A cpu

B cuda:0

C cuda

D cuda:1

💡 Hint

The .to('cuda') method moves the tensor to the default GPU device, usually cuda:0.

The .to('cuda') call moves the tensor to the first GPU device, which is 'cuda:0'. The print statement shows the exact device.

❓ Predict Output

intermediate

What happens when moving a tensor to a non-existent GPU?

What error will this PyTorch code raise if the machine has only one GPU (cuda:0)?

PyTorch

import torch
x = torch.tensor([1, 2, 3])
x = x.to('cuda:1')

A RuntimeError: CUDA error: invalid device ordinal

B TypeError: Expected device string

C No error, tensor moved to cuda:1

D ValueError: Device not found

💡 Hint

Check what happens if you specify a GPU index that does not exist.

If the device index is invalid (like cuda:1 on a single GPU machine), PyTorch raises a RuntimeError about invalid device ordinal.

❓ Model Choice

advanced

Which code correctly moves a model and its input tensor to GPU?

You want to run a PyTorch model on GPU. Which option correctly moves both the model and input tensor to the GPU?

A

model = model.cpu()
input = input.cpu()

B

model = model.to('cpu')
input = input.to('cuda')

C

model = model.cuda()
input = input.cuda()

D

model = model.to('cuda')
input = input.to('cpu')

💡 Hint

Both model and input must be on the same device for computation.

To run on GPU, both model and input must be moved to the GPU device using .cuda() or .to('cuda'). Option C does this correctly.

❓ Hyperparameter

advanced

What is the effect of using .to(device) with a variable device?

Given device = torch.device('cuda' if torch.cuda.is_available() else 'cpu'), what does model.to(device) do?

A Moves model to GPU if available, else CPU

B Always moves model to CPU

C Always moves model to GPU

D Raises error if GPU not available

💡 Hint

The device variable depends on GPU availability.

The device variable is set to 'cuda' if GPU is available, else 'cpu'. model.to(device) moves model accordingly.

🔧 Debug

expert

Why does this code raise a RuntimeError about device mismatch?

Examine the code below and select the reason for the RuntimeError: Expected all tensors to be on the same device.

PyTorch

import torch
model = torch.nn.Linear(2, 2)
input = torch.tensor([[1.0, 2.0]]).to('cuda')
output = model(input)

A Input tensor data type is incorrect

B Input tensor shape is invalid for model

C Model weights are not initialized

D Model is on CPU but input is on GPU, causing device mismatch

💡 Hint

Check where the model and input tensors are located.

The model is on CPU by default, but input is moved to GPU. This causes a device mismatch error during forward pass.