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.

Practice

1. What does the PyTorch method tensor.to('cuda') do?

easy

A. Moves the tensor to the GPU for faster computation

B. Converts the tensor to a CPU tensor

C. Changes the tensor data type to float

D. Deletes the tensor from memory

Solution

1. Step 1: Understand the purpose of to('cuda')

   This method moves the tensor from CPU memory to GPU memory to speed up calculations.

2. Step 2: Recognize the effect on computation

   By moving the tensor to GPU, PyTorch can use GPU cores for faster processing.

3. Final Answer:

   Moves the tensor to the GPU for faster computation -> Option A

4. Quick Check:

   to('cuda') = move tensor to GPU [OK]

Hint: to('cuda') means move tensor to GPU memory [OK]

Common Mistakes:

• Thinking it converts data type
• Assuming it moves tensor to CPU
• Believing it deletes the tensor

2. Which of the following is the correct syntax to move a tensor named x to GPU in PyTorch?

easy

A. x.to('cpu')

B. x.gpu()

C. x.to('cuda')

D. x.cuda('cpu')

Solution

1. Step 1: Identify correct method to move tensor to GPU

   The method to('cuda') moves tensor to GPU.

2. Step 2: Check each option

   x.to('cuda') uses to('cuda'), which is correct. Others either move to CPU or use invalid methods.

3. Final Answer:

   x.to('cuda') -> Option C

4. Quick Check:

   Correct syntax for GPU move = x.to('cuda') [OK]

Hint: Use .to('cuda') to move tensor to GPU [OK]

Common Mistakes:

• Using .to('cpu') instead of 'cuda'
• Calling .cuda('cpu') which is invalid
• Using non-existent .gpu() method

3. What will be the output device of the tensor after running this code?

import torch
x = torch.tensor([1, 2, 3])
if torch.cuda.is_available():
    x = x.cuda()
print(x.device)

medium

A. cuda:0

B. cuda:1

C. cpu

D. None

Solution

1. Step 1: Check if GPU is available

   The code checks torch.cuda.is_available(). If True, it moves tensor to GPU device 0 by default.

2. Step 2: Understand x.device output

   After x.cuda(), the tensor is on GPU device 0, so x.device prints cuda:0.

3. Final Answer:

   cuda:0 -> Option A

4. Quick Check:

   cuda() moves tensor to cuda:0 device [OK]

Hint: cuda() moves tensor to GPU device 0 by default [OK]

Common Mistakes:

• Assuming device is 'cpu' after cuda()
• Thinking cuda() moves to cuda:1 by default
• Expecting None as device

4. Identify the error in this code snippet that tries to move a tensor to GPU:

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

medium

A. Tensor cannot be moved to GPU

B. Tensor must be converted to float before moving

C. Missing .cuda() call after .to()

D. The device string 'gpu' is invalid; should be 'cuda'

Solution

1. Step 1: Check device string in to() method

   The string 'gpu' is not recognized by PyTorch; the correct string is 'cuda'.

2. Step 2: Understand correct usage

   Using 'cuda' moves tensor to GPU. Using 'gpu' causes a runtime error.

3. Final Answer:

   The device string 'gpu' is invalid; should be 'cuda' -> Option D

4. Quick Check:

   Use 'cuda' not 'gpu' in to() [OK]

Hint: Use 'cuda' not 'gpu' as device string [OK]

Common Mistakes:

• Using 'gpu' instead of 'cuda'
• Thinking tensor must be float to move
• Missing .cuda() call after .to()

5. You want to write code that safely moves a tensor x to GPU if available, otherwise keeps it on CPU. Which code snippet correctly does this?

hard

A. x = x.to('cuda') if torch.cuda.is_available() else x.to('gpu')

B. if torch.cuda.is_available():
x = x.to('cuda')
else:
x = x.to('cpu')

C. x = x.cuda() if torch.cuda.is_available() else x.cuda()

D. x = x.to('cpu') if torch.cuda.is_available() else x.to('cuda')

Solution

1. Step 1: Understand device check logic

   We must check if GPU is available using torch.cuda.is_available().

2. Step 2: Apply correct device move

   If GPU is available, move tensor to 'cuda', else keep on 'cpu'. if torch.cuda.is_available(): x = x.to('cuda') else: x = x.to('cpu') does this correctly.

3. Final Answer:

   if torch.cuda.is_available(): x = x.to('cuda') else: x = x.to('cpu') -> Option B

4. Quick Check:

   Check GPU availability before moving tensor [OK]

Hint: Check cuda availability before moving tensor [OK]

Common Mistakes:

• Using invalid device string 'gpu'
• Moving to cuda even if unavailable
• Swapping cpu and cuda in else