Lab 11: Fashion

For Lab 11, you will develop a model to classify images of clothing (fashion).

You are not required to writeup a complete report for this lab! It’s been a long semester and you’ve already written many reports! Simply submit a (blank) template to Canvas for full points.

Because this is the final lab, no late submission will be allowed or accepted.

Background

No background for this lab!

Scenario and Goal

No scenario for this lab!

PyTorch

Unlike other labs, instead of sklearn, you will be required to use PyTorch.

To install PyTorch and a necessary data package, use:

uv pip install torch
uv pip install torchvision

This lab will mostly follow the PyTorch Quickstart guide.

Compute

Completing this lab necessitates access to powerful computational resources.

if torch.cuda.is_available():
    device = "cuda"
elif torch.backends.mps.is_available():
    device = "mps"
else:
    device = "cpu"

print(f"Using {device} device!")

If your machine does not allow for mps or cuda consider using:

Data

The data (and task) for this lab originally comes from Zalando Research.

We will access this data through tools available in pytorch.

Data in Python

The following code can be used to download or re-access the data.

import torch
from torchvision import datasets
from torchvision.transforms import ToTensor

# download training data from open datasets
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# download test data from open datasets
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

The first time this code runs, it will create a directory named data (in the same directory of whatever notebook you are working in), place the data there, and load it. After the first time, running this code again will simply read in the downloaded data.

Like MNIST, there are ten classes for the y data, also represented by integers. The following maps, in order, to the integers 0 to 9.

classes = [
    "T-shirt/top",
    "Trouser",
    "Pullover",
    "Dress",
    "Coat",
    "Sandal",
    "Shirt",
    "Sneaker",
    "Bag",
    "Ankle boot",
]

The X data are 28x28 greyscale images of articles of clothing.

Sample Statistics

Before modeling, be sure to look at the data. Calculate the summary statistics requested on PrairieLearn.

Models

For this lab you will select one model to submit to the autograder. You may use any modeling techniques you’d like, so long as it meets these requirements:

  • Models must be built in PyTorch using nn.Module class.
  • Your model should be created with torch version 2.6.0 or newer.
  • Your model should be created with torchvision version 0.21.0 or newer.
  • Your model should be serialized to TorchScript.
  • Your serialized model must be less than 5MB.

To obtain the maximum points via the autograder, your model must outperform the following metrics:

Test Accuracy: 0.9

Model Persistence

To submit your model to the autograder, you will first need to serialize your model. With a pytorch model named model, convert it to TorchScript. Then, write this object to disk.

# convert to TorchScript
model_scripted = torch.jit.script(model)

# write to disk
model_scripted.save("fashion.pt")

Submission

Before submission, especially of your report, you should be sure to review the Lab Policy document.

On Canvas, be sure to submit both your source .ipynb file and a rendered .html version of the report.