Emotion Detection from Video using YOLOv8 and ResNet18

🚀 Features

🧠 Emotions Detected

🗂️ Project Structure

emotion_yolo_project/
├── models/
│   ├── yolov8n-face.pt              # YOLOv8 face detection model
│   └── resnet18_emotion.pth         # Trained ResNet18 model for emotion classification
├── datasets/                        # FER2013 dataset (organized by class folders)
├── src/
│   ├── emotion_model.py             # Emotion classification logic
│   ├── inference_pipeline.py        # Face detection + emotion pipeline
│   └── train_emotion_model.py       # Training script for ResNet18
├── streamlit_app.py                 # Streamlit UI code
├── requirements.txt                 # Python dependencies
└── Dockerfile                       # Docker build instructions

🔧 Installation

Option 1: Run Locally

# Clone the repository
git clone https://github.com/adityawalture/emotion_yolo_project.git
cd emotion_yolo_project

# Create virtual environment
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows

# Install dependencies
pip install --upgrade pip
pip install -r requirements.txt

# Run the app
streamlit run streamlit_app.py

Option 2: Run with Docker

# Build the image
docker build -t emotion_yolo_ui .

# Run the container
docker run -p 8501:8501 emotion_yolo_ui

📥 Required Downloads

🧾 Requirements

streamlit
torch
torchvision
ultralytics
opencv-python
fastapi
pillow
numpy
tqdm
scikit-learn
python-multipart

🙋‍♂️ Streamlit

Emotion_Yolo