| Fashion MNIST Classification | |
| This is a web application for classifying images of clothing using various machine learning models. The models were trained on the Fashion MNIST dataset, which consists of 70,000 grayscale images of clothing items in 10 categories. | |
| Usage | |
| To use the application, simply upload an image of a clothing item and select a machine learning model from the dropdown menu. The application will then predict the category of clothing the image belongs to and display the predicted label along with the probabilities for each category. | |
| Models | |
| The following machine learning models are available in the application: | |
| K-Nearest Neighbors | |
| Decision Tree | |
| Random Forest | |
| AdaBoost | |
| Gradient Boosting | |
| The models were trained on the Fashion MNIST dataset using scikit-learn and saved as serialized files using pickle and joblib. | |
| Dependencies | |
| The application requires the following Python packages: | |
| tensorflow | |
| scikit-learn | |
| joblib | |
| pillow | |
| gradio | |
| You can install them using pip: | |
| Copy code | |
| pip install -r requirements.txt | |
| Credits | |
| This application was created by Praneeth Kandugula as a project for Saint Louis University . The machine learning models were trained on the Fashion MNIST dataset, which was created by Zalando Research. The web interface was built using Gradio. |