This project is a Flask-based web application that uses YOLO (You Only Look Once) object detection models to perform predictions on uploaded images. The application allows users to choose between two different models: "Anedet AI" and "Diadet AI", which are likely used for medical diagnosis purposes such as detecting signs of anemia or diabetes from images.
- Web-Based Interface: A simple and user-friendly web interface for uploading images.
- Model Selection: Users can select either the "Anedet AI" or "Diadet AI" model for their prediction task.
- Image Prediction: The application accepts common image formats (PNG, JPG, JPEG, WEBP) and performs object detection to identify relevant features.
- Display Results: The prediction output, including the detected class and confidence percentage, is displayed to the user.
- Upload Image: The user selects an image file from their local machine and uploads it through the web interface.
- Choose Model: The user chooses which model ("Anedet AI" or "Diadet AI") to use for the analysis.
- Run Prediction: The Flask backend receives the image and the selected model. It uses the corresponding YOLO model to perform a prediction on the image.
- View Output: The application displays the uploaded image along with the prediction result, showing the detected class and the model's confidence level.
.
├── Anedet AI/
│ ├── best2.pt # YOLO model for Anedet
│ └── model.ipynb # Jupyter notebook for model training
├── Diadet AI/
│ ├── best.pt # YOLO model for Diadet
│ └── model.ipynb # Jupyter notebook for model training
├── app.py # Main Flask application
├── requirements.txt # Python dependencies
├── static/ # CSS, JavaScript, and images
└── templates/
└── index.html # HTML template for the web interface
- Python 3.x
- pip
-
Clone the repository:
git clone https://github.com/Arocoboyy/Andidet.AI.git cd Andidet.AI -
Install dependencies:
pip install -r requirements.txt
-
Start the Flask server:
python app.py
-
Open your browser and navigate to
http://127.0.0.1:5000to use the application.