Learning rate for fine-tuning in TensorFlow - Model Pipeline Trace

Model Pipeline - Learning rate for fine-tuning

This pipeline shows how a pre-trained model is fine-tuned on new data using a smaller learning rate. Fine-tuning helps the model adjust gently to new information without forgetting what it already learned.

Data Flow - 5 Stages

1Load pre-trained model

224 rows x 224 columns x 3 channels→Load a model trained on a large dataset (e.g., ImageNet)→224 rows x 224 columns x 3 channels

An image of a cat with size 224x224 pixels and 3 color channels

↓

2Freeze base layers

224 rows x 224 columns x 3 channels→Freeze weights of early layers to keep learned features→224 rows x 224 columns x 3 channels (frozen layers)

Early layers detecting edges and colors remain unchanged

↓

3Add new classification head

Output from frozen layers→Add new layers for the specific task (e.g., 5 classes)→5 classes output

New layers classify images into 5 categories

↓

4Compile model with small learning rate

Model with frozen base and new head→Set optimizer with a small learning rate (e.g., 0.0001)→Compiled model ready for fine-tuning

Adam optimizer with learning rate 0.0001

↓

5Train on new data

1000 images x 224 x 224 x 3→Fine-tune model weights on new dataset→1000 images x 5 class predictions

Model adjusts weights slightly to new categories

Training Trace - Epoch by Epoch

Loss:
0.9 |************
0.8 |**********  
0.7 |********   
0.6 |*******    
0.5 |*****      
0.4 |****       
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Initial fine-tuning with small learning rate starts improving accuracy
2	0.65	0.72	Loss decreases steadily, accuracy improves
3	0.50	0.80	Model learns new task well without forgetting old features
4	0.45	0.83	Fine-tuning stabilizes, small improvements
5	0.42	0.85	Training converges with good accuracy

Prediction Trace - 5 Layers

Layer 1: Input image

Layer 2: Frozen base layers

Layer 3: New classification head

Layer 4: Softmax activation

Layer 5: Prediction output

Model Quiz - 3 Questions

Why do we use a smaller learning rate during fine-tuning?

A To freeze all layers permanently

B To speed up training drastically

C To adjust the model weights gently without losing previous knowledge

D To increase the model size

Key Insight

Using a smaller learning rate during fine-tuning helps the model adapt to new data carefully, preserving useful features learned before. This leads to steady improvement in accuracy and stable training.

Practice

1. Why is it recommended to use a smaller learning rate when fine-tuning a pre-trained TensorFlow model?

easy

A. To increase the batch size automatically

B. To speed up training drastically

C. To make gentle updates and avoid destroying learned features

D. To skip the need for validation data

Solution

1. Step 1: Understand fine-tuning purpose

   Fine-tuning adjusts a pre-trained model slightly to new data without losing learned knowledge.

2. Step 2: Reason about learning rate effect

   A smaller learning rate makes small changes, preserving useful features learned before.

3. Final Answer:

   To make gentle updates and avoid destroying learned features -> Option C

4. Quick Check:

   Small learning rate = gentle fine-tuning [OK]

Hint: Small learning rate prevents big changes during fine-tuning [OK]

Common Mistakes:

• Using a large learning rate that overwrites learned features
• Ignoring the need to freeze layers before fine-tuning
• Assuming learning rate affects batch size

2. Which of the following TensorFlow code snippets correctly sets a smaller learning rate for fine-tuning?

easy

A. optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001)

B. optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)

C. optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)

D. optimizer = tf.keras.optimizers.Adam(learning_rate=0.1)

Solution

1. Step 1: Identify typical fine-tuning learning rates

   Fine-tuning usually uses smaller rates like 0.0001 to avoid big weight changes.

2. Step 2: Compare given learning rates

   0.0001 is smaller than 0.001, 0.01, and 0.1, making it suitable for fine-tuning.

3. Final Answer:

   optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001) -> Option A

4. Quick Check:

   Smaller learning rate = 0.0001 [OK]

Hint: Pick the smallest learning rate value for fine-tuning [OK]

Common Mistakes:

• Choosing a learning rate too large for fine-tuning
• Confusing learning rate with batch size
• Not using tf.keras.optimizers.Adam correctly

3. Consider this TensorFlow code for fine-tuning a model:

base_model.trainable = True
optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=optimizer, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_data, epochs=3)

What is the likely outcome of using this learning rate during fine-tuning?

medium

A. The model will fine-tune smoothly with stable accuracy improvements

B. The model may have unstable training and lose pre-trained knowledge

C. The training will be very slow but stable

D. The model will skip training and keep old weights

Solution

1. Step 1: Analyze learning rate size

   Learning rate 0.01 is relatively large for fine-tuning, which risks big weight changes.

2. Step 2: Predict training behavior

   Large learning rate can cause unstable training and overwrite useful pre-trained features.

3. Final Answer:

   The model may have unstable training and lose pre-trained knowledge -> Option B

4. Quick Check:

   Large learning rate = unstable fine-tuning [OK]

Hint: Large learning rate can harm fine-tuning stability [OK]

Common Mistakes:

• Assuming higher learning rate always improves training speed
• Ignoring the effect of unfreezing the base model
• Thinking loss function controls learning rate impact

4. You wrote this code to fine-tune a TensorFlow model but notice training loss is not decreasing:

base_model.trainable = True
optimizer = tf.keras.optimizers.Adam(learning_rate=0.1)
model.compile(optimizer=optimizer, loss='categorical_crossentropy')
history = model.fit(train_data, epochs=5)

What is the main issue and how to fix it?

medium

A. Learning rate is too high; reduce it to 0.0001

B. Loss function is wrong; use 'sparse_categorical_crossentropy'

C. Base model should be frozen; set trainable = False

D. Epochs are too few; increase to 50

Solution

1. Step 1: Identify learning rate problem

   Learning rate 0.1 is very high for fine-tuning, causing unstable or no learning.

2. Step 2: Suggest fix

   Lowering learning rate to 0.0001 allows gentle updates and loss decrease.

3. Final Answer:

   Learning rate is too high; reduce it to 0.0001 -> Option A

4. Quick Check:

   High learning rate blocks loss decrease [OK]

Hint: Lower learning rate if loss doesn't improve during fine-tuning [OK]

Common Mistakes:

• Changing loss function unnecessarily
• Freezing base model after unfreezing
• Increasing epochs without fixing learning rate

5. You want to fine-tune a pre-trained TensorFlow model on a small dataset. Which learning rate strategy is best to balance learning speed and stability?

hard

A. Start with a small learning rate (e.g., 0.0001), then gradually increase it

B. Use a large learning rate (e.g., 0.1) from the start for faster training

C. Train all layers from scratch with a medium learning rate (e.g., 0.01)

D. Freeze the base model, train the new layers with a higher learning rate, then unfreeze and fine-tune with a smaller learning rate

Solution

1. Step 1: Understand fine-tuning best practice

   Freeze base model first to train new layers safely with higher learning rate.

2. Step 2: Fine-tune with smaller learning rate after unfreezing

   Unfreeze base model and use smaller learning rate to gently adjust pre-trained weights.

3. Final Answer:

   Freeze the base model, train the new layers with a higher learning rate, then unfreeze and fine-tune with a smaller learning rate -> Option D

4. Quick Check:

   Freeze first, then fine-tune with small learning rate [OK]

Hint: Freeze base, train new layers high LR, then fine-tune low LR [OK]

Common Mistakes:

• Using large learning rate from start causing unstable training
• Training all layers from scratch wasting pre-trained knowledge
• Not freezing base model before fine-tuning