Detaching from computation graph in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to detach the tensor from the computation graph.

PyTorch

import torch
x = torch.tensor([1.0, 2.0, 3.0], requires_grad=True)
y = x * 2
z = y.sum()
detached = y.[1]()

Drag options to blanks, or click blank then click option'

Arequires_grad_

Bclone

Cdetach

Dbackward

Attempts:

3 left

💡 Hint

Common Mistakes

Using clone() does not detach from the graph.

Using backward() is for computing gradients, not detaching.

Using requires_grad_() changes gradient tracking but does not detach.

Using detach() creates a new tensor that shares data but is detached from the computation graph, so gradients won't flow back.

2fill in blank

medium

Complete the code to convert a detached tensor back to a NumPy array.

PyTorch

import torch
x = torch.tensor([4.0, 5.0, 6.0], requires_grad=True)
y = x * 3
detached = y.[1]()
numpy_array = detached.numpy()

Drag options to blanks, or click blank then click option'

Adetach

Bclone

Ccpu

Dnumpy

Attempts:

3 left

💡 Hint

Common Mistakes

Trying to convert a tensor with gradients directly to NumPy causes errors.

Using clone() instead of detach() does not stop gradient tracking.

First, detach the tensor to stop gradient tracking, then move it to CPU if needed, and finally convert to NumPy array. Here, only detach() is needed before numpy().

3fill in blank

hard

Fix the error in the code by detaching the tensor before converting to NumPy.

PyTorch

import torch
x = torch.tensor([7.0, 8.0, 9.0], requires_grad=True)
y = x * 4
numpy_array = y.[1]().numpy()

Drag options to blanks, or click blank then click option'

Adetach

Bclone

Ccpu

Drequires_grad_

Attempts:

3 left

💡 Hint

Common Mistakes

Calling numpy() directly on a tensor with requires_grad=True causes errors.

Using clone() does not detach the tensor.

Calling detach() removes the tensor from the computation graph, allowing safe conversion to NumPy.

4fill in blank

hard

Fill both blanks to detach a tensor and move it to CPU before converting to NumPy.

PyTorch

import torch
x = torch.tensor([10.0, 11.0, 12.0], requires_grad=True)
y = x * 5
result = y.[1]().[2]().numpy()

Drag options to blanks, or click blank then click option'

Adetach

Bcpu

Cclone

Dnumpy

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping the order causes errors.

Using clone() instead of detach() does not stop gradient tracking.

First detach the tensor to stop gradient tracking, then move it to CPU to ensure compatibility before converting to NumPy.

5fill in blank

hard

Fill all three blanks to detach a tensor, move it to CPU, and convert it to a NumPy array.

PyTorch

import torch
x = torch.tensor([13.0, 14.0, 15.0], requires_grad=True)
y = x * 6
numpy_array = y.[1]().[2]().[3]()

Drag options to blanks, or click blank then click option'

Adetach

Bcpu

Cnumpy

Dclone

Attempts:

3 left

💡 Hint

Common Mistakes

Calling numpy() before detach() causes errors.

Using clone() instead of detach() does not detach the tensor.

Detach the tensor to stop gradient tracking, move it to CPU, then convert it to a NumPy array.