Model optimization (quantization, pruning) in TensorFlow - Model Pipeline Trace

Model Pipeline - Model optimization (quantization, pruning)

This pipeline shows how a neural network model is made smaller and faster using two techniques: pruning and quantization. Pruning removes less important connections, and quantization reduces the number size to save memory and speed up predictions.

Data Flow - 5 Stages

1Raw data input

1000 rows x 20 columns→Collect raw features for training→1000 rows x 20 columns

[[0.5, 1.2, ..., 0.3], [0.7, 0.8, ..., 0.1], ...]

↓

2Data preprocessing

1000 rows x 20 columns→Normalize features to range 0-1→1000 rows x 20 columns

[[0.25, 0.6, ..., 0.15], [0.35, 0.4, ..., 0.05], ...]

↓

3Model training

1000 rows x 20 columns→Train a dense neural network→Model with weights (20 inputs, 10 hidden, 1 output)

Weights matrices and biases learned

↓

4Model pruning

Model with weights (dense layers)→Remove 30% of smallest magnitude weights→Model with 70% weights remaining

Weights with many zeros replacing small values

↓

5Model quantization

Pruned model weights (float32)→Convert weights from float32 to int8→Quantized model weights (int8)

Weights stored as smaller 8-bit integers

Training Trace - Epoch by Epoch

Loss
0.7 |****
0.6 |*** 
0.5 |**  
0.4 |**  
0.3 |*   
0.2 |*   
    +---------
     1 5 10 15 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning with moderate loss and accuracy
5	0.40	0.78	Loss decreases and accuracy improves steadily
10	0.25	0.88	Model converges with good accuracy
15	0.22	0.90	Slight improvement, stable training

Prediction Trace - 5 Layers

Layer 1: Input layer

Layer 2: Dense layer with pruning

Layer 3: Activation (ReLU)

Layer 4: Quantized output layer

Layer 5: Final prediction

Model Quiz - 3 Questions

What does pruning do to the model weights?

A Removes small weights to make the model smaller

B Increases the number of weights for better accuracy

C Changes weights to floating point numbers

D Adds new layers to the model

Key Insight

Pruning and quantization help make models smaller and faster without losing much accuracy. Pruning removes unimportant connections, and quantization reduces number size, which is great for running models on devices with limited memory and speed.

Practice

1. What is the main goal of model pruning in TensorFlow model optimization?

easy

A. Remove less important weights to reduce model size

B. Convert model weights to lower precision

C. Add more layers to improve accuracy

D. Increase the batch size during training

Solution

1. Step 1: Understand pruning concept

   Pruning means removing parts of the model that contribute less, usually weights with small values.

2. Step 2: Identify pruning effect

   This reduces model size and speeds up inference by making the model simpler.

3. Final Answer:

   Remove less important weights to reduce model size -> Option A

4. Quick Check:

   Pruning = Remove less important weights [OK]

Hint: Pruning cuts small weights to shrink model size [OK]

Common Mistakes:

• Confusing pruning with quantization
• Thinking pruning adds layers
• Believing pruning changes batch size

2. Which of the following is the correct way to apply post-training quantization in TensorFlow Lite?

easy

A. converter.optimizations = [tf.lite.Optimize.DEFAULT]

B. model.compile(optimizer='adam', loss='mse')

C. tf.keras.layers.Dense(10, activation='relu')

D. model.fit(x_train, y_train, epochs=10)

Solution

1. Step 1: Recognize quantization syntax

   Post-training quantization in TensorFlow Lite uses the converter.optimizations property set to [tf.lite.Optimize.DEFAULT].

2. Step 2: Eliminate unrelated options

   Other options relate to training or model layers, not quantization.

3. Final Answer:

   converter.optimizations = [tf.lite.Optimize.DEFAULT] -> Option A

4. Quick Check:

   Quantization uses converter.optimizations = [tf.lite.Optimize.DEFAULT] [OK]

Hint: Quantization uses converter.optimizations setting [OK]

Common Mistakes:

• Confusing training code with quantization setup
• Using model.compile for quantization
• Applying quantization inside model.fit

3. What will be the output shape of the pruned model after applying TensorFlow Model Optimization pruning API on a model with input shape (None, 28, 28, 1) and a Dense layer with 10 units?

medium

A. (None, 28, 28, 10)

B. (None, 10)

C. (None, 28, 28, 1)

D. (10,)

Solution

1. Step 1: Understand pruning effect on shape

   Pruning removes weights but does not change the model architecture or output shape.

2. Step 2: Identify output shape of Dense layer

   A Dense layer with 10 units outputs shape (None, 10) regardless of pruning.

3. Final Answer:

   (None, 10) -> Option B

4. Quick Check:

   Pruning keeps output shape same = (None, 10) [OK]

Hint: Pruning doesn't change output shape, only weights [OK]

Common Mistakes:

• Thinking pruning changes output dimensions
• Confusing input shape with output shape
• Assuming pruning adds extra dimensions

4. You applied pruning to your TensorFlow model but noticed no size reduction after saving. What is the likely cause?

medium

A. You used quantization instead of pruning

B. Pruning increases model size by adding masks

C. Model was not stripped of pruning wrappers before saving

D. Model was saved in HDF5 format

Solution

1. Step 1: Understand pruning wrappers

   Pruning adds wrappers around layers that must be stripped before saving to reduce size.

2. Step 2: Identify saving step

   If wrappers are not stripped, the saved model keeps extra pruning info, so size doesn't reduce.

3. Final Answer:

   Model was not stripped of pruning wrappers before saving -> Option C

4. Quick Check:

   Strip pruning wrappers before saving = smaller model [OK]

Hint: Strip pruning wrappers before saving model [OK]

Common Mistakes:

• Assuming pruning always reduces size without stripping
• Confusing pruning with quantization effects
• Ignoring model saving format impact

5. You want to optimize a TensorFlow model for deployment on a mobile device with limited memory and CPU. Which combination of techniques is best to reduce model size and speed up inference without much accuracy loss?

hard

A. Convert model to float64 precision

B. Only increase training epochs without optimization

C. Use dropout layers and batch normalization

D. Apply pruning during training and then post-training quantization

Solution

1. Step 1: Identify optimization goals

   For mobile deployment, reducing size and speeding inference are key, while keeping accuracy.

2. Step 2: Choose suitable techniques

   Pruning removes unnecessary weights, quantization reduces number precision, both reduce size and speed up inference.

3. Step 3: Eliminate wrong options

   Increasing epochs doesn't optimize size; dropout and batch norm are for training regularization; float64 increases size.

4. Final Answer:

   Apply pruning during training and then post-training quantization -> Option D

5. Quick Check:

   Pruning + quantization = smaller, faster model [OK]

Hint: Combine pruning and quantization for best optimization [OK]

Common Mistakes:

• Ignoring quantization after pruning
• Confusing training tricks with optimization
• Using higher precision increases size