Replacing classifier head in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of replacing classifier head in a PyTorch model

What is the output shape of the model's final layer after replacing the classifier head with a new linear layer of 10 output features?

PyTorch

import torch
import torch.nn as nn
from torchvision import models

model = models.resnet18()
num_features = model.fc.in_features
model.fc = nn.Linear(num_features, 10)

input_tensor = torch.randn(4, 3, 224, 224)
output = model(input_tensor)
output_shape = output.shape
print(output_shape)

A torch.Size([4, 10])

B torch.Size([4, 1000])

C torch.Size([1, 10])

D torch.Size([4, 512])

💡 Hint

Remember the batch size and the number of output classes in the new classifier head.

Replacing the classifier head changes the output layer to have 10 output features. The batch size is 4, so the output shape is (4, 10).

❓ Model Choice

intermediate

Choosing the correct way to replace classifier head in PyTorch

Which option correctly replaces the classifier head of a pretrained VGG16 model to output 5 classes?

A model.head = nn.Linear(4096, 5)

B model.fc = nn.Linear(512, 5)

C model.classifier = nn.Linear(4096, 5)

D model.classifier[6] = nn.Linear(4096, 5)

💡 Hint

Check the attribute name and index of the classifier layer in VGG16.

VGG16's classifier is a Sequential module, and the last layer is at index 6. Replacing model.classifier[6] correctly changes the output layer.

❓ Hyperparameter

advanced

Effect of freezing layers when replacing classifier head

If you replace the classifier head of a pretrained ResNet50 and freeze all layers except the new head, which statement is true about training?

A All model parameters will update during training.

B Only the new classifier head's parameters will update during training.

C No parameters will update because the model is frozen.

D Only the first convolutional layer will update during training.

💡 Hint

Freezing layers means setting requires_grad to False for those parameters.

Freezing all layers except the new head means only the new head's parameters have requires_grad=True and will update during training.

🔧 Debug

advanced

Debugging error after replacing classifier head

After replacing the classifier head of a pretrained ResNet18 with nn.Linear(512, 20), the model raises a runtime error during training: "size mismatch, m1: [4 x 512], m2: [1000 x 20]". What is the cause?

A The old classifier layer was not replaced properly; the model still uses the original 1000 output features.

B The input tensor batch size is incorrect.

C The new classifier layer has wrong input features; it should be 1000 instead of 512.

D The loss function expects 1000 classes instead of 20.

💡 Hint

Check if the model's classifier attribute was correctly assigned.

The error shows a mismatch between expected input features and the classifier weight matrix, indicating the old classifier was not replaced properly.

🧠 Conceptual

expert

Why replace classifier head instead of retraining entire model?

Why is it common practice to replace only the classifier head of a pretrained model when adapting it to a new task?

A Because retraining the entire model is impossible with pretrained weights.

B Because the classifier head contains all convolutional filters needed for feature extraction.

C Because pretrained layers have learned useful features and retraining only the head saves time and data.

D Because replacing the head increases the model size and improves accuracy automatically.

💡 Hint

Think about transfer learning and feature reuse.

Pretrained layers capture general features; retraining only the head adapts to new classes efficiently without needing large data or long training.