In this project you will discover how to effectively pure Tensorflow to predict the numbers in MNIST dataset as well as in high-level ML api Keras.

Dataset of 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images.

You can learn more about this dataset on the Keras website: https://keras.io/datasets/

In this post, you discovered the MultiClass classification using TF as well as in Keras Deep Learning library in Python.

You learned how you can work through a binary classification problem step-by-step with Keras, specifically:

• How to load and prepare data for use in TF/Keras.
• How to create a neural network model.
• How data preparation schemes can lift the performance of your models.
• How experiments adjusting the network topology can lift model performance.

What things you need to install the software and how to install them

puthon IDE
jupyter notebook

• python - Programming Language
• tensorflow - TensorFlow is an open-source machine learning library for research and production
• keras - Keras is a high-level neural networks API
• numpy - NumPy is the fundamental package for scientific computing

• M.Junaid Fiaz - JD

This project is licensed under the APACHE License - see the LICENSE.md file for details