Freezing layers in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does it mean to 'freeze layers' in a neural network?

Freezing layers means stopping their weights from changing during training. This keeps the learned features fixed while training other parts of the model.

beginner

Why do we freeze layers when using a pre-trained model?

We freeze layers to keep the useful features learned from large data. This saves time and avoids losing good knowledge while training on new data.

beginner

How do you freeze layers in PyTorch?

Set the layer's parameters' requires_grad attribute to False. For example:
for param in model.layer.parameters():
  param.requires_grad = False

intermediate

What happens if you forget to freeze layers when fine-tuning?

The pre-trained weights may change too much, losing useful features. This can cause slower training or worse results.

intermediate

Can you unfreeze layers after freezing them? Why would you do this?

Yes, you can set requires_grad back to True. This is useful to fine-tune the whole model after training only some layers first.

What does setting param.requires_grad = False do in PyTorch?

A Prevents the parameter from updating during training

B Deletes the parameter from the model

C Initializes the parameter with zeros

D Makes the parameter trainable

Setting requires_grad to False tells PyTorch not to compute gradients for that parameter, so it won't update during training.

Why freeze layers in transfer learning?

A To remove layers from the model

B To keep learned features and reduce training time

C To make the model slower

D To increase the model size

Freezing layers keeps the useful features learned before and speeds up training on new tasks.

Which layers are usually frozen first in a convolutional neural network?

A All layers are frozen equally

B Last layers near the output

C Random layers

D Early layers near the input

Early layers learn basic features like edges and textures, so they are often frozen to keep these general features.

What is a common next step after freezing layers and training the new layers?

A Unfreeze some layers and fine-tune the whole model

B Delete the frozen layers

C Stop training immediately

D Freeze more layers

After training new layers, unfreezing some layers allows fine-tuning the whole model for better accuracy.

If you freeze all layers in a model, what will happen during training?

A The model will learn faster

B Only biases will update

C No weights will update, so the model won't learn

D The model will randomly change weights

Freezing all layers means no parameters update, so the model cannot learn from new data.

Explain in your own words what freezing layers means and why it is useful in transfer learning.

Think about how you keep some parts fixed while changing others.

Describe how you would freeze and then unfreeze layers in a PyTorch model during training.

Focus on the requires_grad attribute and training steps.

Practice

1. What does freezing layers in a PyTorch model do during training?

easy

A. Removes the layers from the model

B. Increases the learning rate for those layers

C. Stops the layers' weights from updating

D. Duplicates the layers for faster training

Solution

1. Step 1: Understand freezing layers meaning

   Freezing layers means preventing their weights from changing during training.

2. Step 2: Effect on training

   When frozen, layers do not update weights, so they keep learned features intact.

3. Final Answer:

   Stops the layers' weights from updating -> Option C

4. Quick Check:

   Freezing = no weight updates [OK]

Hint: Freezing means no weight changes during training [OK]

Common Mistakes:

• Thinking freezing increases learning rate
• Believing freezing removes layers
• Assuming freezing duplicates layers

2. Which of the following is the correct way to freeze all parameters in a PyTorch model named model?

easy

A. model.freeze()

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

C. model.requires_grad = False

D. for param in model.parameters(): param.grad = None

Solution

1. Step 1: Identify correct syntax to freeze parameters

   Freezing requires setting requires_grad = False for each parameter.

2. Step 2: Check each option

   for param in model.parameters(): param.requires_grad = False correctly loops over parameters and sets requires_grad = False. Others are invalid or incorrect.

3. Final Answer:

   for param in model.parameters(): param.requires_grad = False -> Option B

4. Quick Check:

   Set requires_grad False to freeze [OK]

Hint: Set requires_grad=False on each parameter to freeze [OK]

Common Mistakes:

• Using model.requires_grad instead of param.requires_grad
• Calling a non-existent freeze() method
• Setting param.grad to None does not freeze

3. Consider this PyTorch code snippet:

import torch.nn as nn
model = nn.Sequential(
  nn.Linear(10, 5),
  nn.ReLU(),
  nn.Linear(5, 2)
)
for param in model[0].parameters():
  param.requires_grad = False

trainable_params = [p for p in model.parameters() if p.requires_grad]
print(len(trainable_params))

What will be printed?

medium

A. 2

B. 4

C. 6

D. 0

Solution

1. Step 1: Analyze model layers and parameters

   model[0] is Linear(10,5) with 2 parameters (weight and bias). model[2] is Linear(5,2) with 2 parameters.

2. Step 2: Check which parameters are trainable

   Parameters in model[0] are frozen (requires_grad=False), so only model[2]'s 2 parameters remain trainable.

3. Final Answer:

   2 -> Option A

4. Quick Check:

   Frozen layer params excluded, trainable = 2 [OK]

Hint: Count only parameters with requires_grad=True [OK]

Common Mistakes:

• Counting all parameters ignoring requires_grad
• Assuming ReLU has parameters
• Confusing layer indices

4. You want to freeze the first layer of a PyTorch model but accidentally wrote:

for param in model.layer1.parameters():
    param.grad = False

What is the problem with this code?

medium

A. param.grad is a tensor, not a boolean flag

B. param.grad disables gradients correctly

C. model.layer1.parameters() does not exist

D. param.requires_grad should be set, not param.grad

Solution

1. Step 1: Understand difference between param.grad and param.requires_grad

   param.grad holds gradient values, it is a tensor or None, not a flag to enable/disable gradients.

2. Step 2: Correct way to freeze parameters

   To freeze, set param.requires_grad = False. Setting param.grad = False is invalid and does not freeze.

3. Final Answer:

   param.requires_grad should be set, not param.grad -> Option D

4. Quick Check:

   Freeze by requires_grad=False, not param.grad [OK]

Hint: Freeze with requires_grad, not param.grad [OK]

Common Mistakes:

• Confusing param.grad with requires_grad
• Trying to disable gradients by setting param.grad
• Assuming param.grad is a boolean

5. You have a pretrained PyTorch model with 3 layers: layer1, layer2, and layer3. You want to freeze layer1 and layer2 but train layer3. Which code correctly freezes only the first two layers?

hard

A. for layer in [model.layer1, model.layer2]:
for param in layer.parameters():
param.requires_grad = False

B. for param in model.parameters():
param.requires_grad = False
for param in model.layer3.parameters():
param.requires_grad = False

C. model.layer1.requires_grad = False
model.layer2.requires_grad = False

D. model.freeze_layers(['layer1', 'layer2'])

Solution

1. Step 1: Understand freezing multiple layers

   Freezing means setting requires_grad = False on each parameter in the layers to freeze.

2. Step 2: Evaluate options

   for layer in [model.layer1, model.layer2]: for param in layer.parameters(): param.requires_grad = False correctly loops over layer1 and layer2 parameters and freezes them correctly. for param in model.parameters(): param.requires_grad = False for param in model.layer3.parameters(): param.requires_grad = False incorrectly freezes all parameters including layer3. model.layer1.requires_grad = False model.layer2.requires_grad = False tries to set requires_grad on layers (invalid). model.freeze_layers(['layer1', 'layer2']) calls a non-existent method.

3. Final Answer:

   for layer in [model.layer1, model.layer2]: for param in layer.parameters(): param.requires_grad = False -> Option A

4. Quick Check:

   Freeze layers by setting requires_grad False per parameter [OK]

Hint: Freeze layers by looping params and setting requires_grad False [OK]

Common Mistakes:

• Setting requires_grad on layer objects instead of parameters
• Using non-existent freeze_layers method
• Freezing all parameters