Repository files navigation

BrainTumorDetection_MLOPS is a FastAPI-based brain tumor detection system designed with MLOps principles for efficient model deployment, automated data handling, and seamless API integration. The system uses MLflow for model tracking, DVC for data versioning, and DAGsHub as the central server for both MLflow and DVC. It employs a Vision Transformer (ViT) model for accurate tumor detection from medical images.

• FastAPI-based API for real-time predictions.
• MLflow integration to track model performance and experiments.
• DVC (Data Version Control) for handling datasets efficiently.
• DAGsHub as a unified platform for MLflow and DVC.
• Automated pipeline for data processing and deployment.

• FastAPI - Web framework for serving the model.
• MLflow - Model tracking and experiment logging.
• DVC - Data versioning and management.
• DAGsHub - Hosting and integration for MLflow and DVC.

git clone https://github.com/RijoSLal/BrainTumorDetection_MLOPS.gitcd BrainTumorDetection_MLOPS

python -m venv venvsource venv/bin/activate# On Windows: venv\Scripts\activate

pip install -r requirements.txt

dvc initdvc remote add origin https://dagshub.com/yourusername/BrainTumorDetection_MLOPS.dvc

export MLFLOW_TRACKING_URI=https://dagshub.com/yourusername/BrainTumorDetection_MLOPS.mlflow

uvicorn main:app --host 0.0.0.0 --port 8000

• Endpoint:/docs
• Method:POST
• Payload:

  {"image":"base64_encoded_image"}

• Response:

  {"prediction":"No abnormal growth detected. However, consult a doctor for confirmation"}

Feel free to contribute.

This project is licensed under the MIT License.