https://github.com/rjohnpaul/fashion_mnist_models
This Python script utilizes TensorFlow to build and train a neural network for classifying images from the Fashion MNIST dataset. The dataset comprises 70,000 grayscale images categorized into 10 classes of clothing
https://github.com/rjohnpaul/fashion_mnist_models
Last synced: 3 days ago
JSON representation
This Python script utilizes TensorFlow to build and train a neural network for classifying images from the Fashion MNIST dataset. The dataset comprises 70,000 grayscale images categorized into 10 classes of clothing
- Host: GitHub
- URL: https://github.com/rjohnpaul/fashion_mnist_models
- Owner: RJohnPaul
- License: mit
- Created: 2024-01-07T12:18:07.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-01-09T01:44:43.000Z (over 1 year ago)
- Last Synced: 2025-01-20T07:44:02.563Z (5 months ago)
- Language: Python
- Homepage: https://bit.ly/fashion_mod
- Size: 3.24 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TensorFlow Fashion MNIST Classifier
.png)
This py script utilizes TensorFlow to train a neural network for classifying images from Fashion MNIST dataset. The dataset consists of a set of 70,000 grayscale images categorized into 10 classes of clothing.
## Features
- Loading and displaying images from the Fashion MNIST dataset.
- Normalizing pixel values to the range [0, 1].
- Building a simple neural network using TensorFlow's Sequential API.
- Compiling the model with the Adam optimizer and sparse categorical crossentropy loss.
- Training the model on the training set for 5 epochs.
- Evaluating the model's performance on the test set.
- Making predictions on the test set.
## Modules Used
- TensorFlow (`import tensorflow as tf`) - [TensorFlow Website](https://www.tensorflow.org/)
- Matplotlib (`import matplotlib.pyplot as plt`) - [Matplotlib Website](https://matplotlib.org/)
-
## Demo
- Try the code out live on Collab : [Demo](https://bit.ly/fashion_mod)
## Installation
Make sure you have TensorFlow and Matplotlib installed using the following commands:
```bash
pip install tensorflow matplotlib
```
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Future Improvements
Possible enhancements and future improvements to the script include:
- Hyperparameter tuning for optimizing model performance.
- Experimenting with different neural network architectures.
- Implementing data augmentation techniques to improve model generalization.
- Visualizing model performance metrics and training progress.
Feel free to contribute and explore further improvements!
---