Mlflow-TensorFlow-Image-Classification-Guide

Welcome to the Mlflow-TensorFlow-Guide project, created and maintained by Kailash Parshad, an Ethical Hacker, Penetration Tester, and Cybersecurity Enthusiast.

Install links

• Python 3.10.11: Python 3.10.11
• Anaconda: Anaconda
• VScode: VSCODE

Instruction Video

Watch the Instruction Video

Project Overview

This project is a TensorFlow and MLflow demonstration, showcasing the process of building, training, and evaluating a machine learning model using TensorFlow. It provides a step-by-step guide on how to set up the environment, load data, preprocess it, build and compile a model, and evaluate its performance.

Project Links

• GitHub Repository: Mlflow-TensorFlow-Guide
• LinkedIn: Kailash Parshad's LinkedIn Profile

Getting Started

To get started with this project, follow these steps:

1. Create a Conda Environment:

   • Create a Conda environment to isolate the project dependencies.

2. Activate the Environment:

   • Activate the newly created Conda environment.

3. Install Jupyter Notebook:

   • Install Jupyter Notebook to run the provided Jupyter Notebook.

4. Install Dependencies:

   • Install project dependencies using pip.

5. Tensorflow Model Building

   • Follow the Guide pdf

6. Recording Tensorflow model with MLflow

   • Follow the Guide pdf

Project Structure

The project is structured as follows:

• Notebook: The main notebook for running the code is available here.

Building and Compiling the Model

In the notebook, the following key steps are demonstrated:

1. Import necessary libraries, including TensorFlow, MLflow, and more.
2. Load and preprocess fashion MNIST dataset.
3. Build a neural network model using TensorFlow.
4. Compile the model with loss and optimizer.
5. Train the model with training and validation data.

Model Evaluation

The model's performance is evaluated on the test dataset, and accuracy metrics are reported.

Usage

You can use this project as a guide to working with TensorFlow and MLflow for building and evaluating machine learning models.

Acknowledgments

• TensorFlow: Official TensorFlow Website
• MLflow: Official MLflow Website

References

• TensorFlow Classification Tutorial

Thank You

Thank you for exploring the Mlflow-TensorFlow-Guide project. If you have any questions or suggestions, feel free to reach out to Kailash Parshad.