Model optimization (quantization, pruning) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply dynamic quantization to a PyTorch model.

PyTorch

import torch
import torch.nn as nn

model = nn.Linear(10, 5)
quantized_model = torch.quantization.[1](model, {nn.Linear})

Drag options to blanks, or click blank then click option'

Aquantize_static

Bquantize_dynamic

Cquantize_per_tensor

Dquantize_per_channel

Attempts:

3 left

💡 Hint

Common Mistakes

Using static quantization function instead of dynamic.

Passing wrong module types to the quantization function.

Dynamic quantization is applied using torch.quantization.quantize_dynamic for modules like nn.Linear.

2fill in blank

medium

Complete the code to prune 20% of the weights in the first linear layer using L1 unstructured pruning.

PyTorch

import torch.nn.utils.prune as prune

prune.l1_unstructured(model.[1], name='weight', amount=0.2)

Drag options to blanks, or click blank then click option'

Abias

Blinear1

Clayer1

Dweight

Attempts:

3 left

💡 Hint

Common Mistakes

Trying to prune the 'bias' parameter instead of 'weight'.

Using the layer name instead of the parameter name.

Pruning targets the weight parameter of the layer, so model.weight is used.

3fill in blank

hard

Fix the error in the code to remove pruning reparameterization from the linear layer.

PyTorch

prune.[1](model.linear, 'weight')

Drag options to blanks, or click blank then click option'

Aremove

Bunprune

Cclear

Dreset

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-existent functions like 'unprune' or 'clear'.

Trying to delete the layer instead of removing pruning.

The correct function to remove pruning is prune.remove.

4fill in blank

hard

Fill both blanks to apply global unstructured pruning to two layers with 30% sparsity.

PyTorch

parameters_to_prune = [(model.fc1, 'weight'), (model.fc2, 'weight')]
prune.[1](parameters_to_prune, pruning_method=prune.[2], amount=0.3)

Drag options to blanks, or click blank then click option'

Aglobal_unstructured

Bl1_unstructured

Crandom_unstructured

Dstructured

Attempts:

3 left

💡 Hint

Common Mistakes

Using structured pruning method with global pruning function.

Mixing pruning methods and functions incorrectly.

Global pruning is done with global_unstructured and the pruning method is l1_unstructured.

5fill in blank

hard

Fill all three blanks to create a quantized model, prepare it for static quantization, and convert it.

PyTorch

model.qconfig = torch.quantization.get_default_[1]_qconfig('fbgemm')
torch.quantization.[2](model, inplace=True)
quantized_model = torch.quantization.[3](model)

Drag options to blanks, or click blank then click option'

Aqconfig

Bprepare

Cconvert

Dcalibrate

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing 'calibrate' with 'prepare' or 'convert'.

Skipping the prepare step before convert.

For static quantization, set qconfig, then prepare the model, and finally convert it.