Fine-tuning strategy in PyTorch - Model Pipeline Trace

Model Pipeline - Fine-tuning strategy

This pipeline shows how a pre-trained model is adapted to a new task by fine-tuning. We start with a model trained on a large dataset, then adjust its weights slightly using new task data to improve performance.

Data Flow - 6 Stages

1Load pre-trained model

N/A→Load a model trained on a large dataset (e.g., ImageNet)→Model with fixed architecture and pre-trained weights

ResNet50 model with weights trained on ImageNet

↓

2Replace final layer

Model with output layer for 1000 classes→Replace last layer to match new task classes (e.g., 10 classes)→Model with output layer for 10 classes

Replace ResNet50's 1000-class layer with a 10-class layer

↓

3Freeze base layers

Model with all layers trainable→Freeze weights of all layers except the new final layer→Model with only final layer trainable

Freeze convolutional layers, train only classifier layer

↓

4Train final layer

Training data: 5000 images x 3 channels x 224 x 224→Train only the final layer on new data→Updated final layer weights

Train classifier on 5000 labeled images for 5 epochs

↓

5Unfreeze some layers

Model with final layer trained→Unfreeze last few layers to fine-tune→Model with last layers trainable

Unfreeze last 2 convolutional blocks

↓

6Fine-tune entire model

Training data: 5000 images x 3 channels x 224 x 224→Train unfrozen layers with a low learning rate→Fine-tuned model weights

Train for 10 epochs with learning rate 0.0001

Training Trace - Epoch by Epoch

Loss
1.2 |*       
1.0 | *      
0.8 |  *     
0.6 |   *    
0.4 |    *   
0.2 |       *
    +--------
     1 3 5 10
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.55	Training only final layer starts with moderate loss and accuracy
3	0.8	0.70	Loss decreases and accuracy improves as final layer learns
5	0.6	0.78	Final layer training converges with good accuracy
6	0.58	0.80	Unfreeze last layers and continue training with low learning rate
8	0.45	0.85	Fine-tuning improves model performance further
10	0.40	0.88	Loss decreases steadily, accuracy reaches high level

Prediction Trace - 5 Layers

Layer 1: Input image

Layer 2: Feature extraction layers (frozen)

Layer 3: New classifier layer (trainable)

Layer 4: Softmax activation

Layer 5: Prediction

Model Quiz - 3 Questions

Why do we freeze most layers at the start of fine-tuning?

A Because frozen layers improve accuracy automatically

B To speed up training by removing layers

C To keep learned features and train only the new task-specific layer

D To prevent the model from making any predictions

Key Insight

Fine-tuning leverages existing knowledge in a pre-trained model by first training only new layers, then carefully adjusting deeper layers with a low learning rate. This approach helps the model adapt to new tasks efficiently while preserving useful features.

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