Dropout (nn.Dropout) in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of Dropout layer during training

What is the output of the following PyTorch code snippet when the model is in training mode?

PyTorch

import torch
import torch.nn as nn

torch.manual_seed(0)
dropout = nn.Dropout(p=0.5)
input_tensor = torch.tensor([1.0, 2.0, 3.0, 4.0])
output = dropout(input_tensor)
print(output)

A tensor([2., 0., 6., 8.])

B tensor([1., 2., 3., 4.])

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

D tensor([0.5, 1., 1.5, 2.])

💡 Hint

Remember that dropout randomly zeroes some elements and scales the others by 1/(1-p) during training.

During training, nn.Dropout with p=0.5 randomly sets half of the input elements to zero and scales the remaining elements by 1/(1-0.5) = 2. Given the fixed seed, the output tensor is [2., 0., 6., 8.].

🧠 Conceptual

intermediate

Effect of Dropout during evaluation

What happens to the output of nn.Dropout when the model is switched to evaluation mode (model.eval())?

A Dropout randomly zeros some inputs and scales the rest.

B Dropout sets all inputs to zero.

C Dropout scales the input by the dropout probability p.

D Dropout passes the input through unchanged without any modification.

💡 Hint

Think about why dropout is only used during training.

During evaluation, dropout is disabled and acts as an identity function, passing inputs unchanged to ensure consistent predictions.

❓ Hyperparameter

advanced

Choosing dropout probability

Which dropout probability (p) value is generally recommended to prevent overfitting without causing underfitting in a neural network?

A p = 0.5 (moderate dropout)

B p = 0.1 (very low dropout)

C p = 0.0 (no dropout)

D p = 0.9 (very high dropout)

💡 Hint

Typical dropout values are between 0.2 and 0.5.

A dropout probability around 0.5 is commonly used to balance regularization and model capacity, reducing overfitting without hurting learning too much.

🔧 Debug

advanced

Identifying error in dropout usage

What error will occur when running this code snippet?

PyTorch

import torch
import torch.nn as nn

dropout = nn.Dropout(p=1.2)
input_tensor = torch.tensor([1.0, 2.0, 3.0])
output = dropout(input_tensor)
print(output)

A ValueError: input tensor shape mismatch

B RuntimeError: dropout probability has to be between 0 and 1

C No error, outputs tensor with all zeros

D TypeError: input_tensor must be float type

💡 Hint

Check the valid range for dropout probability p.

Dropout probability p must be between 0 and 1 inclusive. Setting p=1.2 causes a runtime error.

❓ Model Choice

expert

Best place to apply dropout in a neural network

Where is the best place to apply nn.Dropout in a feedforward neural network to improve generalization?

A After the output layer

B Before the input layer

C Between hidden layers after activation functions

D Only on the final prediction output

💡 Hint

Dropout is usually applied to internal layers to prevent co-adaptation of neurons.

Applying dropout between hidden layers after activations helps regularize the network by randomly dropping neurons during training.

Practice

1. What is the main purpose of using nn.Dropout in a PyTorch model?

easy

A. To increase the learning rate automatically

B. To add noise to the input data

C. To randomly disable neurons during training to prevent overfitting

D. To speed up the training process by skipping layers

Solution

1. Step 1: Understand dropout's role in training

   Dropout randomly disables neurons during training to reduce overfitting by preventing co-adaptation of neurons.

2. Step 2: Compare options with dropout purpose

   Only To randomly disable neurons during training to prevent overfitting correctly describes dropout's function; others describe unrelated concepts.

3. Final Answer:

   To randomly disable neurons during training to prevent overfitting -> Option C

4. Quick Check:

   Dropout = random neuron disabling [OK]

Hint: Dropout disables neurons randomly during training only [OK]

Common Mistakes:

• Thinking dropout speeds up training
• Confusing dropout with data augmentation
• Believing dropout changes learning rate

2. Which of the following is the correct way to create a dropout layer with 30% dropout rate in PyTorch?

easy

A. nn.Dropout(30)

B. nn.Dropout(p=30)

C. nn.Dropout(rate=0.3)

D. nn.Dropout(0.3)

Solution

1. Step 1: Check PyTorch dropout syntax

   The dropout layer takes a float between 0 and 1 as the probability of dropout, passed as the first argument or named 'p'.

2. Step 2: Validate each option

   nn.Dropout(0.3) uses nn.Dropout(0.3) which is correct. nn.Dropout(p=30) uses p=30 (invalid, should be 0.3). nn.Dropout(rate=0.3) uses 'rate' which is not a valid argument. nn.Dropout(30) passes 30 (integer) which is invalid.

3. Final Answer:

   nn.Dropout(0.3) -> Option D

4. Quick Check:

   Dropout probability is float 0-1 [OK]

Hint: Dropout probability is a float between 0 and 1 [OK]

Common Mistakes:

• Using integer instead of float for dropout rate
• Using wrong argument name like 'rate'
• Passing percentage as whole number

3. Consider the following PyTorch code snippet:

import torch
import torch.nn as nn

layer = nn.Dropout(0.5)
input_tensor = torch.ones(4)
layer.train()
output_train = layer(input_tensor)
layer.eval()
output_eval = layer(input_tensor)
print(output_train)
print(output_eval)

What will be the output of print(output_eval)?

medium

A. A tensor of all ones: tensor([1., 1., 1., 1.])

B. A tensor with some zeros randomly placed

C. A tensor of all zeros

D. An error because dropout is disabled in eval mode

Solution

1. Step 1: Understand dropout behavior in eval mode

   Dropout disables neuron dropping during evaluation mode and passes input unchanged.

2. Step 2: Analyze output_eval value

   Since layer.eval() is called before output_eval, the output will be the same as input: all ones tensor.

3. Final Answer:

   A tensor of all ones: tensor([1., 1., 1., 1.]) -> Option A

4. Quick Check:

   Dropout off in eval mode = input unchanged [OK]

Hint: Dropout disables only in eval mode, output equals input [OK]

Common Mistakes:

• Expecting dropout to apply in eval mode
• Confusing train() and eval() modes
• Thinking dropout outputs zeros always

4. You wrote this PyTorch code but the dropout layer seems to have no effect during training:

import torch.nn as nn
layer = nn.Dropout(0.4)
output = layer(input_tensor)

What is the most likely reason dropout is not working as expected?

medium

A. Dropout only works on GPU tensors

B. You forgot to call layer.train() to enable dropout

C. The dropout probability 0.4 is too low to see effect

D. You need to call layer.eval() to activate dropout

Solution

1. Step 1: Recall dropout behavior in train vs eval modes

   Dropout only disables neurons during training mode. In eval mode, dropout is disabled.

2. Step 2: Identify missing train mode call

   If layer.train() is not called (e.g., after a previous layer.eval()), the layer stays in eval mode, so dropout has no effect.

3. Final Answer:

   You forgot to call layer.train() to enable dropout -> Option B

4. Quick Check:

   Dropout active only in train mode [OK]

Hint: Call train() to activate dropout during training [OK]

Common Mistakes:

• Assuming dropout works without train() mode
• Thinking dropout depends on tensor device
• Calling eval() instead of train()

5. You want to add dropout to a neural network to reduce overfitting. Which of the following is the best practice when using nn.Dropout in your model?

hard

A. Apply dropout only during training and disable it during evaluation

B. Apply dropout during both training and evaluation for consistency

C. Apply dropout only during evaluation to test robustness

D. Apply dropout only to the input layer and never to hidden layers

Solution

1. Step 1: Understand dropout's intended use

   Dropout is designed to randomly disable neurons during training to prevent overfitting.

2. Step 2: Recall dropout behavior during evaluation

   During evaluation, dropout is disabled to use the full network for predictions.

3. Step 3: Evaluate options

   Apply dropout only during training and disable it during evaluation correctly states dropout is applied only during training. Options B and C are incorrect because dropout should not be active during evaluation. Apply dropout only to the input layer and never to hidden layers is incorrect because dropout can be applied to hidden layers as well.

4. Final Answer:

   Apply dropout only during training and disable it during evaluation -> Option A

5. Quick Check:

   Dropout active in train, off in eval [OK]

Hint: Dropout off during eval, on during training [OK]

Common Mistakes:

• Applying dropout during evaluation
• Limiting dropout only to input layer
• Confusing dropout with data augmentation