Fine-tuning strategy in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is fine-tuning in machine learning?

Fine-tuning is the process of taking a pre-trained model and training it a bit more on a new, often smaller, dataset to adapt it to a specific task.

beginner

Why do we freeze some layers during fine-tuning?

We freeze layers to keep their learned features unchanged, which helps prevent overfitting and reduces training time by only updating certain parts of the model.

intermediate

In PyTorch, how do you freeze layers of a model?

You set the parameter's requires_grad attribute to False, like:
for param in model.parameters():
param.requires_grad = False

intermediate

What is a common strategy to fine-tune a pre-trained model?

First, freeze most layers and train only the last layers. Then, optionally unfreeze some earlier layers and train with a smaller learning rate.

beginner

How does using a smaller learning rate help during fine-tuning?

A smaller learning rate helps make small adjustments to the pre-trained weights, avoiding large changes that could ruin the learned features.

What does freezing layers in a model mean?

A Stopping updates to those layers during training

B Removing those layers from the model

C Adding more neurons to those layers

D Changing the activation function of those layers

Freezing layers means their weights do not get updated during training.

Why start fine-tuning by training only the last layers?

A Because last layers have fewer parameters

B Because last layers do not affect output

C Because last layers are always frozen

D Because last layers are usually task-specific

Last layers capture task-specific features, so training them first adapts the model quickly.

In PyTorch, which attribute controls if a parameter is trainable?

A grad_enabled

B trainable

C requires_grad

D update_flag

The requires_grad attribute controls if gradients are computed and parameters updated.

What is a benefit of using a pre-trained model for fine-tuning?

A It guarantees perfect accuracy

B It reduces training time and data needed

C It removes the need for validation

D It makes the model smaller

Pre-trained models have learned useful features, so fine-tuning needs less data and time.

What happens if you use a large learning rate during fine-tuning?

A The model might forget learned features

B The model trains faster without issues

C The model becomes smaller

D The model ignores new data

A large learning rate can cause big changes that ruin the pre-trained knowledge.

Explain the step-by-step process of fine-tuning a pre-trained model in PyTorch.

Think about which layers to freeze and how to adjust learning rates.

Describe why fine-tuning is useful compared to training a model from scratch.

Consider the benefits of transfer learning.

Practice

1. What is the main purpose of fine-tuning a pre-trained PyTorch model?

easy

A. To adjust the model to perform well on a new task by training some layers

B. To train the model from scratch on a large dataset

C. To reduce the model size by removing layers

D. To convert the model to a different programming language

Solution

1. Step 1: Understand fine-tuning concept

   Fine-tuning means taking a model already trained on one task and adjusting it to work well on a new task by training some of its layers.

2. Step 2: Compare options

   Only To adjust the model to perform well on a new task by training some layers describes this process correctly. Other options describe unrelated actions.

3. Final Answer:

   To adjust the model to perform well on a new task by training some layers -> Option A

4. Quick Check:

   Fine-tuning = Adjust model layers for new task [OK]

Hint: Fine-tuning means training some layers for a new task [OK]

Common Mistakes:

• Thinking fine-tuning means training from scratch
• Confusing fine-tuning with model compression
• Assuming fine-tuning changes the whole model

2. Which PyTorch code snippet correctly freezes all layers except the last one for fine-tuning?

easy

A. model.freeze_all_layers()
model.unfreeze_last_layer()

B. for param in model.parameters(): param.requires_grad = True
for param in model.fc.parameters(): param.requires_grad = False

C. model.requires_grad = False
model.fc.requires_grad = True

D. for param in model.parameters(): param.requires_grad = False
for param in model.fc.parameters(): param.requires_grad = True

Solution

1. Step 1: Understand freezing layers in PyTorch

   Setting param.requires_grad = False freezes a layer so it won't update during training.

2. Step 2: Analyze code snippets

   for param in model.parameters(): param.requires_grad = False for param in model.fc.parameters(): param.requires_grad = True freezes all parameters first, then unfreezes only the last layer (model.fc). The other options reverse or misuse this logic or use non-existent methods.

3. Final Answer:

   for param in model.parameters(): param.requires_grad = False for param in model.fc.parameters(): param.requires_grad = True -> Option D

4. Quick Check:

   Freeze all, unfreeze last layer = for param in model.parameters(): param.requires_grad = False for param in model.fc.parameters(): param.requires_grad = True [OK]

Hint: Freeze all with requires_grad=False, then unfreeze last layer [OK]

Common Mistakes:

• Setting requires_grad True for all layers by mistake
• Using non-existent PyTorch methods
• Forgetting to unfreeze the last layer

3. Given this PyTorch code for fine-tuning, what will be the output of print(sum(p.requires_grad for p in model.parameters()))?

for param in model.parameters():
    param.requires_grad = False
for param in model.classifier.parameters():
    param.requires_grad = True
print(sum(p.requires_grad for p in model.parameters()))

medium

A. Number of all model parameters

B. Number of parameters in model.classifier

C. Zero

D. Raises an error

Solution

1. Step 1: Understand requires_grad flags

   All parameters are first frozen (requires_grad=False). Then only parameters in model.classifier are unfrozen (requires_grad=True).

2. Step 2: Calculate sum of requires_grad

   Summing p.requires_grad counts how many parameters are trainable. Since only model.classifier parameters are True, the sum equals their count.

3. Final Answer:

   Number of parameters in model.classifier -> Option B

4. Quick Check:

   Only classifier params require grad = Number of parameters in model.classifier [OK]

Hint: Sum requires_grad counts trainable parameters [OK]

Common Mistakes:

• Assuming all parameters are trainable
• Confusing boolean sum with total parameters
• Expecting an error from this code

4. You tried to fine-tune a model by freezing layers but the training loss does not change. What is the most likely error in your PyTorch code?

medium

A. You used the wrong optimizer

B. You forgot to set model.train() before training

C. You did not set requires_grad = True for any parameters

D. You replaced the last layer with wrong output size

Solution

1. Step 1: Analyze symptom - loss not changing

   If loss stays the same, model parameters are not updating during training.

2. Step 2: Check requires_grad flags

   If all parameters have requires_grad = False, gradients won't be computed and weights won't update, causing no loss change.

3. Final Answer:

   You did not set requires_grad = True for any parameters -> Option C

4. Quick Check:

   No trainable params = no loss change [OK]

Hint: Check requires_grad True for trainable layers [OK]

Common Mistakes:

• Assuming optimizer choice causes no loss change
• Forgetting to call model.train() but blaming loss
• Ignoring requires_grad flags

5. You want to fine-tune a pre-trained ResNet model on a 10-class problem. Which strategy is best to start with?

hard

A. Freeze all layers, replace the final fully connected layer with 10 outputs, and train only this layer

B. Train the entire ResNet model from scratch with 10 output classes

C. Freeze only the first convolutional layer and train the rest

D. Replace the final layer but keep all layers trainable without freezing

Solution

1. Step 1: Understand common fine-tuning approach

   Starting by freezing all layers except the last layer is a common strategy to adapt a pre-trained model to a new task efficiently.

2. Step 2: Evaluate options

   Freeze all layers, replace the final fully connected layer with 10 outputs, and train only this layer matches this approach: freeze all, replace last layer for 10 classes, train only last layer. Other options either train from scratch or do not freeze enough layers, which can be inefficient or unstable.

3. Final Answer:

   Freeze all layers, replace the final fully connected layer with 10 outputs, and train only this layer -> Option A

4. Quick Check:

   Freeze all but last layer for new task [OK]

Hint: Freeze all, replace last layer, train only it first [OK]

Common Mistakes:

• Training entire model from scratch unnecessarily
• Freezing too few layers causing slow training
• Not replacing last layer to match output classes