Activation functions (ReLU, Sigmoid, Softmax) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply the ReLU activation function to the tensor.

PyTorch

import torch
import torch.nn.functional as F

x = torch.tensor([-1.0, 0.0, 1.0, 2.0])
output = F.[1](x)
print(output)

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

Arelu

Bsigmoid

Csoftmax

Dtanh

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid or softmax instead of relu for this task.

Forgetting to import torch.nn.functional as F.

The ReLU function replaces negative values with zero and keeps positive values unchanged. Using F.relu applies this activation.

2fill in blank

medium

Complete the code to apply the Sigmoid activation function to the tensor.

PyTorch

import torch
import torch.nn.functional as F

x = torch.tensor([-2.0, 0.0, 2.0])
output = F.[1](x)
print(output)

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

Asoftmax

Brelu

Csigmoid

Dlog_softmax

Attempts:

3 left

💡 Hint

Common Mistakes

Using ReLU instead of Sigmoid for probability outputs.

Using softmax when only one dimension is present.

The Sigmoid function outputs values between 0 and 1, useful for probabilities. Using F.sigmoid applies this activation.

3fill in blank

hard

Fix the error in applying Softmax activation along the correct dimension.

PyTorch

import torch
import torch.nn.functional as F

x = torch.tensor([[1.0, 2.0, 3.0], [1.0, 2.0, 3.0]])
output = F.softmax(x, dim=[1])
print(output)

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

A0

B1

C2

D-1

Attempts:

3 left

💡 Hint

Common Mistakes

Using dim=0 applies softmax across batches, which is usually incorrect.

Using dim=2 causes an index error for 2D tensors.

Softmax is usually applied along the feature dimension (dim=1) to convert scores into probabilities per row.

4fill in blank

hard

Fill both blanks to create a tensor and apply ReLU activation.

PyTorch

import torch
import torch.nn.functional as F

x = torch.tensor([1])
output = F.[2](x)
print(output)

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

A[[-1.0, 0.0, 1.0], [2.0, -2.0, 3.0]]

B[1, 2, 3]

Crelu

Dsigmoid

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid instead of relu changes output range.

Using a 1D tensor when a 2D tensor is expected.

The tensor contains positive and negative values. Applying relu sets negatives to zero and keeps positives.

5fill in blank

hard

Fill all three blanks to create a tensor, apply Softmax along the correct dimension, and print the result.

PyTorch

import torch
import torch.nn.functional as F

x = torch.tensor([1])
output = F.[2](x, dim=[3])
print(output)

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

A[[2.0, 1.0, 0.1], [1.0, 3.0, 0.2]]

Brelu

C1

Dsoftmax

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu instead of softmax changes output meaning.

Using dim=0 applies softmax across batches, not features.

The tensor has two rows of scores. Applying softmax along dim=1 converts each row into probabilities.