This repository contains a project that performs facial keypoint detection using Convolutional Neural Networks (CNNs). The model was trained on a dataset of facial images and their corresponding facial keypoints using PyTorch.
To get started with this project, follow the instructions below:
To run this project, you need to have the following software installed:
- Python 3.x
- PyTorch
- OpenCV
- Matplotlib
- NumPy
- Jupyter Notebook
To install the required software, follow the instructions below:
-
Install Python 3.x from the official Python website.
-
Install PyTorch by following the instructions on the official PyTorch website.
-
Install OpenCV by running the following command:
pip install opencv-python
- Install Matplotlib by running the following command:
pip install matplotlib
- Install NumPy by running the following command:
pip install numpy
- Install Jupyter Notebook by running the following command:
pip install jupyter
To use this project, follow the instructions below:
- Clone this repository by running the following command:
git clone https://github.com/OmarEhab007/Facial__Keypoint_Detection.git
- Navigate to the cloned repository by running the following command:
cd Facial__Keypoint_Detection
- Launch Jupyter Notebook by running the following command:
jupyter notebook
-
Open the Facial_Keypoint_Detection.ipynb notebook in Jupyter Notebook.
-
Follow the instructions in the notebook to train the model and perform facial keypoint detection on an image.
The dataset used in this project is the Facial Keypoints Detection dataset, which contains 7049 training images and 1783 test images. The dataset includes images with faces marked with 68 facial keypoints, such as the corners of the mouth and the eyes.
- This project was inspired by the Udacity Computer Vision Nanodegree Program.
- The dataset used in this project was obtained from the Kaggle Facial Keypoints Detection competition.