Deep Learning Track WiSe 24/25
Deep Learning Track WiSe 24/25
Deep Learning Track WiSe 24/25
  • Welcome to the Deep Learning Track
  • Setup
  • Learning Material
  • Section 1 - The Math
    • Derivatives and Gradients
    • Vectors, Matrices and Tensors
    • The power of matrix computation
    • Exercise - Matrix Computation
  • Section 2 - The Data
    • PyTorch Datasets and Data Loaders
    • Working with Data Tables
    • Exercise - Loading Data from a CSV file
    • Working with Images
    • Exercise - Image Datasets
    • Working with Text
  • Section 3 - Neural Networks
    • Activation Functions
    • Exercise - Activation Functions
    • Exercise - The Softmax Function
    • The Neuron
    • Two type of applications: Regression and Classification
    • Loss Functions
    • Exercise - Regression Loss Functions
    • Exercise - Classification Loss Functions
    • The Gradient Descent Algorithm
    • Exercise - Implementing Gradient Descent
    • Exercise - PyTorch Autograd
    • Exercise - Regression with Neural Networks
    • Exercise - Classification with Neural Networks
    • Playground - Neural Networks
  • Section 4 - Convolutional Neural Networks
    • Convolution
    • Convolutional Neural Networks
    • Classifying handwritten digits
    • Playground - Convolutional Neural Networks
    • Transfer Learning
  • Final Project - Text Classification
  • Further Resources
    • Computer Vision Libraries
    • Image Classification with PyTorch
    • Object Detection with PyTorch
    • Deep AI Explainability
Powered by GitBook
On this page
  • Choose a dataset
  • The Notebook
  • Project Submission

Final Project - Text Classification

Now that you have worked through the course exercises it is time for the final project. You will build a text classifier for classifying text into multiple categories.

PreviousTransfer LearningNextFurther Resources

Choose a dataset

The goal of the final image classification project is to train a convolutional neural network on a dataset of your choice. Kaggle is a nice platform where you can find big datasets that you can use for your project. Please share the link to the dataset you have used in your final submission.

Here are some datasets that you could use:

  • Cat and Dog images (2 classes):

  • CT Scans for COVID 19 (3 classes):

  • Food classification (35 classes

  • Flower Imge classification (102 classes):

  • Mushroom classification (215 classes)

  • Bird Image Classification (525 classes)

You can find more public datasets at Kaggle .

The Notebook

Your task is to download a dataset of your choice and the following notebook. The notebook contains the code for finetuning a pretrained convolutional neuran network with PyTorch. The code has already been written for you, so you only need to make this notebook run on your machine and answer the three questions in the notebook after you have trained the model.

Project Submission

When you have trained your model we expect you to send us the following artifacts:

  • The notebook with all the cell outputs after the training. You can export the notebook as an HTML document.

  • The model weights

  • The three questions in the notebook must be answered. You can write down the answers in the notebook.

https://www.kaggle.com/competitions/dogs-vs-cats/data
https://www.kaggle.com/datasets/azaemon/preprocessed-ct-scans-for-covid19
https://www.kaggle.com/datasets/harishkumardatalab/food-image-classification-dataset
https://www.kaggle.com/datasets/thanatoz/flower-classification-dataset
https://www.kaggle.com/datasets/daniilonishchenko/mushrooms-images-classification-215
https://www.kaggle.com/datasets/gpiosenka/100-bird-species
here
37KB
Image-Classifier-Project.ipynb