Model optimization (quantization, pruning) in PyTorch - 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: quantization and pruning. Quantization reduces the number size used in the model, and pruning removes unnecessary parts of the model. This helps the model run efficiently on devices with less power.

Data Flow - 6 Stages

1Original Data Input

1000 rows x 28 x 28 pixels→Load grayscale images of handwritten digits→1000 rows x 28 x 28 pixels

Image of digit '7' represented as 28x28 pixel values

↓

2Preprocessing

1000 rows x 28 x 28 pixels→Normalize pixel values to range 0-1→1000 rows x 28 x 28 pixels

Pixel value 150 becomes 0.59

↓

3Feature Engineering

1000 rows x 28 x 28 pixels→Flatten images into 784-length vectors→1000 rows x 784 columns

28x28 image becomes a list of 784 numbers

↓

4Model Training

1000 rows x 784 columns→Train a simple neural network with 1 hidden layer→Model with weights and biases

Weights matrix shape: 784 x 128

↓

5Model Pruning

Model with weights and biases→Remove 30% of smallest weights (set to zero)→Model with 30% fewer active weights

Weights matrix now has 70% non-zero values

↓

6Model Quantization

Model with pruned weights (float32)→Convert weights from 32-bit floats to 8-bit integers→Model with quantized weights (int8)

Weight 0.1234 float32 becomes 12 int8

Training Trace - Epoch by Epoch

Loss
0.7 |*       
0.6 | *      
0.5 |  *     
0.4 |   *    
0.3 |    **  
0.2 |      * 
    +--------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.75	Model starts learning, loss is high, accuracy moderate
2	0.45	0.85	Loss decreases, accuracy improves
3	0.35	0.90	Model converges well, good accuracy
4	0.30	0.92	Slight improvement, model stabilizes
5	0.28	0.93	Final epoch, model ready for optimization

Prediction Trace - 5 Layers

Layer 1: Input Layer

Layer 2: Hidden Layer (Dense)

Layer 3: Pruning Applied

Layer 4: Quantization Applied

Layer 5: Output Layer (Softmax)

Model Quiz - 3 Questions

What does pruning do to the model weights?

A Increases the size of weights

B Removes small weights by setting them to zero

C Changes weights to floating point numbers

D Adds more weights to the model

Key Insight

Model optimization techniques like pruning and quantization help make models smaller and faster without losing much accuracy. Pruning removes unimportant weights, and quantization reduces number size. This is important for running models on devices with limited resources.

Practice

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

easy

A. Add more training data to improve accuracy

B. Increase the number of layers in the model

C. Change the model architecture to a different type

D. Remove less important weights to make the model smaller

Solution

1. Step 1: Understand pruning concept

   Pruning means removing weights that do not contribute much to the model's output.

2. Step 2: Identify pruning effect

   Removing these weights makes the model smaller and faster without changing its structure.

3. Final Answer:

   Remove less important weights to make the model smaller -> Option D

4. Quick Check:

   Pruning = Remove less important weights [OK]

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

Common Mistakes:

• Thinking pruning adds layers
• Confusing pruning with data augmentation
• Believing pruning changes model type

2. Which PyTorch function is used to apply pruning to a layer?

easy

A. torch.nn.utils.prune.l1_unstructured

B. torch.quantization.quantize_dynamic

C. torch.optim.Adam

D. torch.nn.functional.relu

Solution

1. Step 1: Identify pruning functions in PyTorch

   PyTorch pruning utilities are in torch.nn.utils.prune module.

2. Step 2: Match pruning function

   l1_unstructured is a common pruning method that removes weights based on L1 norm.

3. Final Answer:

   torch.nn.utils.prune.l1_unstructured -> Option A

4. Quick Check:

   Pruning function = l1_unstructured [OK]

Hint: Pruning uses torch.nn.utils.prune functions [OK]

Common Mistakes:

• Confusing pruning with quantization functions
• Choosing optimizer functions by mistake
• Selecting activation functions instead of pruning

3. What will be the output shape of the model's weight tensor after applying this pruning code?

import torch
import torch.nn.utils.prune as prune

layer = torch.nn.Linear(4, 3)
prune.l1_unstructured(layer, name='weight', amount=0.5)
print(layer.weight.shape)

medium

A. torch.Size([4, 3]) with half weights removed

B. torch.Size([3, 4]) with half weights removed physically

C. torch.Size([3, 4]) with some weights zeroed

D. torch.Size([4, 3]) unchanged

Solution

1. Step 1: Check layer weight shape

   A Linear layer with input 4 and output 3 has weight shape (3, 4).

2. Step 2: Understand pruning effect on weight tensor

   Pruning sets some weights to zero but does not change tensor shape.

3. Final Answer:

   torch.Size([3, 4]) with some weights zeroed -> Option C

4. Quick Check:

   Pruning zeros weights, shape stays same [OK]

Hint: Pruning zeros weights but keeps tensor shape [OK]

Common Mistakes:

• Thinking pruning changes tensor shape
• Confusing input/output dimensions order
• Assuming weights are physically removed

4. Identify the error in this PyTorch pruning code:

import torch.nn.utils.prune as prune
layer = torch.nn.Linear(5, 2)
prune.l1_unstructured(layer, name='bias', amount=0.3)

medium

A. Missing import for torch

B. Layer input and output sizes are invalid

C. Amount must be an integer, not float

D. Cannot prune bias with l1_unstructured

Solution

1. Step 1: Examine the code imports

   The code imports only prune but attempts to use torch.nn.Linear without importing torch.

2. Step 2: Identify the runtime error

   This causes NameError: name 'torch' is not defined when creating the layer.

3. Final Answer:

   Missing import for torch -> Option A

4. Quick Check:

   Missing torch import causes NameError [OK]

Hint: Import torch before using torch.nn [OK]

Common Mistakes:

• Overlooking missing torch import
• Thinking pruning bias is unsupported
• Assuming amount must be integer

5. You want to speed up inference on a PyTorch model by reducing number precision. Which approach should you use?

hard

A. Increase batch size during training

B. Apply dynamic quantization to convert weights to lower precision

C. Prune 90% of the model weights randomly

D. Add dropout layers to the model

Solution

1. Step 1: Understand quantization purpose

   Quantization reduces number precision (e.g., float32 to int8) to speed up inference.

2. Step 2: Identify correct method

   Dynamic quantization in PyTorch converts weights to lower precision without retraining.

3. Step 3: Compare other options

   Pruning removes weights but may not speed inference as much; batch size and dropout affect training, not inference speed.

4. Final Answer:

   Apply dynamic quantization to convert weights to lower precision -> Option B

5. Quick Check:

   Quantization = lower precision for speed [OK]

Hint: Quantization reduces precision to speed inference [OK]

Common Mistakes:

• Confusing pruning with quantization
• Thinking batch size affects model speed directly
• Adding dropout to speed inference