NumPy bridge (from_numpy, numpy) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does torch.from_numpy() do in PyTorch?

It converts a NumPy array into a PyTorch tensor that shares the same memory. Changes to one affect the other.

beginner

How can you convert a PyTorch tensor back to a NumPy array?

Use the .numpy() method on the tensor. The returned NumPy array shares memory with the tensor.

intermediate

Why is sharing memory between PyTorch tensors and NumPy arrays useful?

It allows fast data exchange without copying, saving memory and time when switching between PyTorch and NumPy.

beginner

What happens if you modify a PyTorch tensor created from a NumPy array?

The original NumPy array will also change because they share the same memory.

intermediate

Can you use torch.from_numpy() with NumPy arrays that are not contiguous in memory?

No, the NumPy array must be contiguous. Otherwise, you should call .copy() on the array before conversion.

What does torch.from_numpy(numpy_array) return?

A A copy of the NumPy array as a tensor

B A PyTorch tensor sharing memory with the NumPy array

C A NumPy array converted to a list

D An error if the array is not float type

torch.from_numpy() creates a tensor that shares memory with the original NumPy array, so no data is copied.

How do you convert a PyTorch tensor t back to a NumPy array?

A <code>t.numpy()</code>

B <code>numpy.array(t)</code>

C <code>torch.to_numpy(t)</code>

D <code>t.to_numpy()</code>

The .numpy() method on a tensor returns a NumPy array sharing the same data.

If you change a PyTorch tensor created from a NumPy array, what happens to the NumPy array?

A It becomes detached

B It stays the same

C It raises an error

D It changes too

Because they share memory, changes to the tensor affect the NumPy array.

What must be true about a NumPy array before using torch.from_numpy()?

A It must be of integer type

B It must be 1-dimensional

C It must be contiguous in memory

D It must be a copy

The array must be contiguous; otherwise, conversion may fail or produce unexpected results.

Why is the NumPy bridge between PyTorch and NumPy useful?

A It allows fast data sharing without copying

B It converts tensors to images

C It speeds up GPU computations

D It automatically normalizes data

Sharing memory avoids copying data, making operations faster and more memory efficient.

Explain how PyTorch tensors and NumPy arrays can share data using the NumPy bridge.

Think about memory sharing and conversion methods.

Describe a situation where using the NumPy bridge between PyTorch and NumPy is beneficial.

Consider performance and interoperability.

Practice

1. What does torch.from_numpy() do in PyTorch?

easy

A. Converts a PyTorch tensor into a NumPy array

B. Creates a new PyTorch tensor with random values

C. Converts a NumPy array into a PyTorch tensor sharing the same memory

D. Converts a Python list into a NumPy array

Solution

1. Step 1: Understand the function purpose

   torch.from_numpy() is designed to take a NumPy array and create a PyTorch tensor from it.

2. Step 2: Memory sharing behavior

   The created tensor shares the same memory with the original NumPy array, so changes in one affect the other.

3. Final Answer:

   Converts a NumPy array into a PyTorch tensor sharing the same memory -> Option C

4. Quick Check:

   from_numpy() converts NumPy array to tensor [OK]

Hint: Remember from_numpy links tensor to NumPy array memory [OK]

Common Mistakes:

• Confusing from_numpy with tensor.numpy()
• Thinking it copies data instead of sharing memory
• Assuming it creates a tensor from a Python list

2. Which of the following is the correct syntax to convert a PyTorch tensor t back to a NumPy array?

easy

A. t.numpy()

B. t.to_numpy()

C. torch.from_numpy(t)

D. numpy(t)

Solution

1. Step 1: Identify the method to convert tensor to NumPy

   PyTorch tensors have a method called numpy() that returns a NumPy array sharing the same data.

2. Step 2: Check syntax correctness

   The correct syntax is calling t.numpy() on the tensor object.

3. Final Answer:

   t.numpy() -> Option A

4. Quick Check:

   tensor.numpy() converts tensor to NumPy array [OK]

Hint: Use tensor.numpy() to get NumPy array from tensor [OK]

Common Mistakes:

• Using numpy(t) which is invalid
• Confusing from_numpy with numpy()
• Using a non-existent method like to_numpy()

3. What will be the output of the following code?

import torch
import numpy as np
np_array = np.array([1, 2, 3])
tensor = torch.from_numpy(np_array)
np_array[0] = 10
print(tensor)

medium

A. Error because tensor is immutable

B. tensor([1, 2, 3])

C. tensor([0, 2, 3])

D. tensor([10, 2, 3])

Solution

1. Step 1: Understand memory sharing between NumPy and tensor

   The tensor created by torch.from_numpy() shares memory with the NumPy array, so changes in the array affect the tensor.

2. Step 2: Analyze the code change

   Changing np_array[0] to 10 updates the shared memory, so the tensor reflects this change.

3. Final Answer:

   tensor([10, 2, 3]) -> Option D

4. Quick Check:

   Shared memory means tensor updates with NumPy changes [OK]

Hint: Changing NumPy array updates tensor from from_numpy() [OK]

Common Mistakes:

• Assuming tensor is independent and unchanged
• Thinking tensor is immutable and throws error
• Confusing tensor.numpy() with from_numpy()

4. Identify the error in this code snippet:

import torch
import numpy as np
np_array = np.array([1, 2, 3])
tensor = torch.from_numpy(np_array)
tensor += 1
print(np_array)

medium

A. No error; np_array will print [2, 3, 4]

B. RuntimeError because tensor is not writable

C. SyntaxError due to invalid operator

D. np_array remains unchanged as tensor is a copy

Solution

1. Step 1: Understand memory sharing

   Tensors from torch.from_numpy() share memory with NumPy arrays, so in-place operations like += modify both.

2. Step 2: Analyze the operation

   tensor += 1 performs in-place addition on the shared memory. No error occurs, and np_array becomes [2, 3, 4].

3. Final Answer:

   No error; np_array will print [2, 3, 4] -> Option A

4. Quick Check:

   In-place ops on from_numpy tensors modify NumPy array [OK]

Hint: In-place ops on from_numpy tensors modify NumPy array [OK]

Common Mistakes:

• Thinking it causes RuntimeError because tensor not writable
• Assuming tensor is independent copy
• Confusing with syntax error

5. You have a NumPy array arr = np.array([1, 2, 3]). You want to create a PyTorch tensor from it, modify the tensor without affecting the original array, and then convert the tensor back to a NumPy array. Which code snippet achieves this correctly?

hard

A. tensor = torch.from_numpy(arr)
tensor[0] = 10
new_arr = tensor.numpy()

B. tensor = torch.tensor(arr)
tensor[0] = 10
new_arr = tensor.numpy()

C. tensor = torch.from_numpy(arr)
tensor.clone()
tensor[0] = 10
new_arr = tensor.numpy()

D. tensor = torch.tensor(arr)
arr[0] = 10
new_arr = tensor.numpy()

Solution

1. Step 1: Understand memory sharing and cloning

   torch.from_numpy() shares memory with the NumPy array, so modifying the tensor changes the array. Using torch.tensor() creates a copy, so changes don't affect the original.

2. Step 2: Check each option

   tensor = torch.from_numpy(arr) tensor[0] = 10 new_arr = tensor.numpy() shares memory, so modifies arr.
   tensor = torch.from_numpy(arr) tensor.clone() tensor[0] = 10 new_arr = tensor.numpy() calls clone() without assigning back to tensor, so tensor remains shared and modifies arr.
   tensor = torch.tensor(arr) tensor[0] = 10 new_arr = tensor.numpy() creates an independent copy, safe.
   tensor = torch.tensor(arr) arr[0] = 10 new_arr = tensor.numpy() modifies arr directly.

3. Final Answer:

   tensor = torch.tensor(arr) tensor[0] = 10 new_arr = tensor.numpy() -> Option B

4. Quick Check:

   Use torch.tensor() to avoid shared memory [OK]

Hint: Use torch.tensor() to copy and avoid shared memory [OK]

Common Mistakes:

• Using from_numpy and modifying tensor affects original array
• Calling clone() without reassigning the tensor
• Modifying original array instead of tensor