This repository contains code for a Facial Emotion Recognition project. The goal of this project is to build and train a deep learning model that can recognize emotions from facial expressions in images.
In this project, we utilize a convolutional neural network (CNN) architecture to perform facial emotion recognition. The code is implemented using PyTorch and includes the following components:
- Loading a file containing image data and labels
- Data preprocessing and transformation
- Creating custom datasets and data loaders
- Model architecture definition
- Model training and evaluation
The dataset used for this project is FER2013, which contains facial expression images labeled with various emotions. The dataset is split into training and validation sets.
-
Clone this repository:
git clone https://github.com/Aayush518/Facial_Emotion_Recognition.git cd Facial_Emotion_Recognition
-
Install the required dependencies:
pip install torch pandas scikit-learn torchvision numpy matplotlib Pillow torchsummary tqdm
-
Place the FER2013 dataset CSV file (e.g.,
fer2013_mini_XCEPTION.csv
) in the project directory. -
Run the data preprocessing and model training code:
python Train_Model.py
-
Evaluate the trained model:
python Trained.py
Include information about the model's performance on the validation set and any additional insights or visualizations.