# Final Project - Text Classification

## 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): <https://www.kaggle.com/competitions/dogs-vs-cats/data>
* CT Scans for COVID 19 (3 classes):\
  <https://www.kaggle.com/datasets/azaemon/preprocessed-ct-scans-for-covid19>
* Food classification (35 classes\
  <https://www.kaggle.com/datasets/harishkumardatalab/food-image-classification-dataset>
* Flower Imge classification (102 classes):\
  <https://www.kaggle.com/datasets/thanatoz/flower-classification-dataset>
* Mushroom classification (215 classes)\
  <https://www.kaggle.com/datasets/daniilonishchenko/mushrooms-images-classification-215>
* Bird Image Classification (525 classes)\
  <https://www.kaggle.com/datasets/gpiosenka/100-bird-species>

You can find more public datasets at Kaggle [here](https://www.kaggle.com/datasets).

### 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.

{% file src="<https://content.gitbook.com/content/0yllaCQ5tDTzssP05wwd/blobs/wHTlzikxU7qqEeqxZDb2/Image-Classifier-Project.ipynb>" %}

### 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.