Replacing classifier head in PyTorch

Introduction

We replace the classifier head to change what the model predicts. This helps when using a pre-trained model for a new task with different output classes.

You want to use a pre-trained model but with a different number of output classes.

You need to adapt a model trained on one dataset to work on another dataset.

You want to fine-tune only the last layer for faster training.

You want to experiment with different classifier designs on top of a fixed feature extractor.

Syntax

PyTorch

model.classifier = torch.nn.Linear(in_features, out_features)

model.classifier is the part of the model that makes final predictions.

in_features must match the output size of the previous layer.

Examples

Replace classifier with a linear layer that outputs 10 classes, assuming input features are 512.

PyTorch

model.classifier = torch.nn.Linear(512, 10)

For models like ResNet, the classifier is often called fc. This replaces it to output 5 classes.

PyTorch

model.fc = torch.nn.Linear(2048, 5)

Sample Model

This code loads a pre-trained ResNet18 model, replaces its classifier head to output 3 classes, and runs a dummy input through it. It prints the original classifier size, the output shape, and the output values.

PyTorch

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

# Load a pre-trained ResNet18 model
model = models.resnet18(pretrained=True)

# Check original classifier (fc) output features
print(f'Original classifier output features: {model.fc.out_features}')

# Replace the classifier head to output 3 classes
model.fc = nn.Linear(model.fc.in_features, 3)

# Create dummy input tensor (batch size 1, 3 color channels, 224x224 image)
dummy_input = torch.randn(1, 3, 224, 224)

# Get model output
output = model(dummy_input)

# Print output shape and values
print(f'Output shape: {output.shape}')
print(f'Output values: {output}')

Important Notes

Always match the input features of the new classifier to the previous layer's output size.

Replacing the classifier head is common in transfer learning.

After replacing, you usually need to train or fine-tune the new head.

Summary

Replacing the classifier head lets you adapt a model to new tasks.

Use the correct input and output sizes for the new layer.

This is a key step in transfer learning with PyTorch models.

Practice

1. What is the main reason to replace the classifier head in a pretrained PyTorch model?

easy

A. To adapt the model to a new task with different output classes

B. To speed up the training by removing layers

C. To reduce the model size by deleting layers

D. To change the input image size the model accepts

Solution

1. Step 1: Understand the classifier head role

   The classifier head is the last layer that decides the output classes based on learned features.

2. Step 2: Reason about adapting to new tasks

   Replacing the classifier head allows the model to output predictions for new classes different from the original training.

3. Final Answer:

   To adapt the model to a new task with different output classes -> Option A

4. Quick Check:

   Classifier head replacement = new task adaptation [OK]

Hint: Classifier head controls output classes, replace for new tasks [OK]

Common Mistakes:

• Thinking replacing head changes input size
• Assuming it reduces model size significantly
• Believing it speeds up training by removing layers

2. Which of the following is the correct way to replace the classifier head of a pretrained ResNet model in PyTorch for 10 output classes?

easy

A. model.fc = nn.Linear(2048, 10)

B. model.classifier = nn.Linear(2048, 10)

C. model.fc = nn.Linear(512, 10)

D. model.head = nn.Linear(512, 10)

Solution

1. Step 1: Identify ResNet classifier attribute

   ResNet models use model.fc as the classifier head.

2. Step 2: Check input feature size for ResNet

   ResNet50 and similar have 2048 features before the classifier, so input size is 2048.

3. Final Answer:

   model.fc = nn.Linear(2048, 10) -> Option A

4. Quick Check:

   ResNet classifier = model.fc with 2048 input features [OK]

Hint: ResNet classifier is model.fc with 2048 input features [OK]

Common Mistakes:

• Using wrong attribute like model.classifier or model.head
• Using wrong input size like 512 instead of 2048
• Confusing ResNet with other models like VGG

3. Given the code below, what will be the output shape of the model's final layer after replacement?

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

model = models.resnet18(pretrained=True)
model.fc = nn.Linear(512, 5)

input_tensor = torch.randn(1, 3, 224, 224)
output = model(input_tensor)
print(output.shape)

medium

A. torch.Size([1, 1000])

B. torch.Size([1, 512])

C. torch.Size([1, 5])

D. torch.Size([3, 224, 224])

Solution

1. Step 1: Understand the replaced classifier output size

   The new classifier layer outputs 5 values per input (5 classes).

2. Step 2: Check input batch size and output shape

   Input batch size is 1, so output shape is (1, 5).

3. Final Answer:

   torch.Size([1, 5]) -> Option C

4. Quick Check:

   Output shape = (batch_size, output_classes) = (1, 5) [OK]

Hint: Output shape matches batch size and new class count [OK]

Common Mistakes:

• Expecting original 1000 classes output
• Confusing feature size with output size
• Misreading input tensor shape as output

4. You tried replacing the classifier head of a pretrained model with model.fc = nn.Linear(1024, 10) but got a runtime error during training. What is the most likely cause?

medium

A. The model.fc attribute does not exist in pretrained models

B. The output size 10 is too large for the model

C. You forgot to call model.eval() before training

D. The input feature size 1024 does not match the model's actual output features

Solution

1. Step 1: Check input feature size for classifier

   The input size to the new Linear layer must match the output features of the previous layer.

2. Step 2: Identify mismatch causing runtime error

   If 1024 is incorrect, the model will raise size mismatch errors during forward pass.

3. Final Answer:

   The input feature size 1024 does not match the model's actual output features -> Option D

4. Quick Check:

   Input size mismatch causes runtime error [OK]

Hint: Match Linear input size to previous layer output features [OK]

Common Mistakes:

• Assuming output size causes error
• Confusing eval mode with training errors
• Thinking model.fc is missing in pretrained models

5. You want to fine-tune a pretrained ResNet50 on a dataset with 15 classes. Which code snippet correctly replaces the classifier head and freezes all layers except the new head?

hard

A. model = models.resnet50(pretrained=True)
model.fc = nn.Linear(2048, 15)
for param in model.parameters():
param.requires_grad = False

B. model = models.resnet50(pretrained=True)
for param in model.parameters():
param.requires_grad = False
model.fc = nn.Linear(2048, 15)

C. model = models.resnet50(pretrained=True)
for param in model.fc.parameters():
param.requires_grad = False
model.fc = nn.Linear(2048, 15)

D. model = models.resnet50(pretrained=True)
model.fc = nn.Linear(512, 15)
for param in model.parameters():
param.requires_grad = True

Solution

1. Step 1: Freeze all existing model parameters

   Set param.requires_grad = False for all parameters to prevent updates during training.

2. Step 2: Replace classifier head with correct input/output sizes

   ResNet50's classifier input size is 2048; output size is 15 for new classes.

3. Step 3: Ensure new head parameters are trainable

   By replacing model.fc after freezing, new layer parameters default to requires_grad=True.

4. Final Answer:

   Freeze all params, then replace head with nn.Linear(2048, 15) -> Option B

5. Quick Check:

   Freeze old layers, replace head with correct sizes [OK]

Hint: Freeze before replacing head to keep new layer trainable [OK]

Common Mistakes:

• Freezing after replacing head disables new layer training
• Using wrong input size 512 instead of 2048
• Not freezing any layers when fine-tuning