https://github.com/udacity-machinelearning-internship/image_classifier
Image classifier project for Udacity "Intro to machine learning with tensorflow" program.
https://github.com/udacity-machinelearning-internship/image_classifier
Last synced: 5 months ago
JSON representation
Image classifier project for Udacity "Intro to machine learning with tensorflow" program.
- Host: GitHub
- URL: https://github.com/udacity-machinelearning-internship/image_classifier
- Owner: Udacity-MachineLearning-Internship
- Created: 2024-09-21T18:59:17.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-12T19:17:21.000Z (about 1 year ago)
- Last Synced: 2025-03-28T01:57:51.148Z (9 months ago)
- Language: Jupyter Notebook
- Size: 46.7 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README

  [](https://www.python.org/downloads/release/python-380/)
[](https://pypi.org/project/pip/21.0/)

[](https://github.com/BaraSedih11/image_classifier/releases/tag/v1.0.0)
[](https://github.com/BaraSedih11/image_classifier/graphs/contributors)

This project demonstrates the implementation of an image classification model using **TensorFlow**. It utilizes **transfer learning** with a pre-trained **MobileNet** model to classify images into multiple categories, showcasing the power of modern machine learning techniques.
## Project Overview
- **Dataset**: The model is trained on the **Oxford Flowers 102** dataset.
- **Model**: Transfer learning with MobileNet for feature extraction.
- **Application**: A command-line tool for image classification.
## Features
- Data preprocessing pipelines for resizing and normalizing images.
- Transfer learning for efficient model training.
- Command-line application for inference, including top-K predictions and class mapping.
## Technologies Used
- **Python**
- **TensorFlow** and **TensorFlow Hub**
- **Matplotlib** for data visualization
## Installation and Usage
1. Clone the repository:
```bash
git clone https://github.com/BaraSedih11/image_classifier.git
```
2. Install the required libraries:
```bash
pip install -r requirements.txt
```
3. Train the model:
```bash
python train.py
```
4. Use the trained model to classify images:
```bash
python predict.py --image_path --model_path
```
## Results
* Achieved high accuracy in classifying flower species using transfer learning.
* Provided a flexible and easy-to-use tool for image classification tasks.