This repository contains the code and resources for the Object Localization with TensorFlow project completed on Coursera.
This project is a guided project offered on Coursera. It focuses on creating and training an Object Localization model using TensorFlow's Keras API. The project aims to teach participants how to create a convolutional neural network (CNN) to classify as well as localize emojis in images. Localization, in this context, refers to determining the position of the emojis in the images. The CNN model is designed to have one input and two outputs.
- Duration: 2 hours
- Prerequisites: Prior programming experience in Python, familiarity with TensorFlow, theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like Gradient Descent.
- Format: Practical, hands-on guided project for learners who want to understand how to use TensorFlow to solve computer vision tasks like Object Localization.
The project is structured as follows:
- Introduction
- Downloading and Visualizing Data
- Creating Examples
- Plotting Bounding Boxes
- Data Generator
- Model Creation
- Custom Metric: IoU
- Compiling the Model
- Custom Callback
- Model Training
- Coursera Project Link: Object Localization with TensorFlow
- TensorFlow Documentation: https://www.tensorflow.org/
Special thanks to Coursera for offering this guided project.
The code and resources in this repository are based on the guided project offered on Coursera and may have specific usage terms. Please refer to the Coursera project materials for more information.