Freezing and unfreezing layers in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

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

Freezing layers means making their weights unchangeable during training. This keeps the learned features intact while training other parts of the model.

beginner

Why would you freeze layers when using transfer learning?

You freeze layers to keep the useful features learned from a large dataset and only train new layers for your specific task. This saves time and avoids losing good features.

beginner

How do you freeze layers in TensorFlow Keras?

Set the layer's 'trainable' property to False, for example: layer.trainable = False. Then recompile and train the model.

intermediate

What does 'unfreezing' layers mean and when is it useful?

Unfreezing means allowing previously frozen layers to update their weights during training. It is useful for fine-tuning the whole model after initial training.

intermediate

What is a common workflow involving freezing and unfreezing layers?

First, freeze base layers and train new layers. Then unfreeze some or all base layers and continue training with a low learning rate to fine-tune.

What happens when you set layer.trainable = False in TensorFlow?

A The layer's weights do not update during training

B The layer's weights are reset to zero

C The layer is removed from the model

D The layer trains faster

Setting layer.trainable = False freezes the layer so its weights stay fixed during training.

Why freeze layers in transfer learning?

A To make the model smaller

B To speed up data loading

C To keep learned features and avoid retraining all layers

D To increase the number of layers

Freezing layers keeps the useful features learned from previous data and focuses training on new layers.

When is unfreezing layers most useful?

A Before compiling the model

B During fine-tuning after initial training

C When initializing the model

D When saving the model

Unfreezing allows updating weights to fine-tune the model after training new layers.

What must you do after changing layer.trainable before training?

A Recompile the model

B Restart Python

C Save the model

D Nothing, just train

You must recompile the model so the training configuration updates with the new trainable settings.

Which is a typical step in freezing and unfreezing workflow?

A Freeze all layers and never train

B Unfreeze all layers at the start

C Train only frozen layers

D Freeze base layers, train new layers, then unfreeze base layers for fine-tuning

This workflow helps keep learned features and then fine-tunes the whole model carefully.

Explain the concept of freezing and unfreezing layers in neural networks and why it is important in transfer learning.

Think about keeping learned features fixed vs. updating them.

Describe the steps to freeze and then unfreeze layers in a TensorFlow Keras model during training.

Remember to recompile after changing trainable status.