utkarsh1706 / Chicken-Disease-Classification

This project is a comprehensive MLOps endeavor focused on classifying chicken diseases using advanced deep learning techniques, particularly LSTM neural networks. Leveraging Docker and DVC (Data Version Control), the pipeline is meticulously crafted to streamline the deployment and management of the deep learning model.

Chicken-Disease-Classification

Overview

This project is a comprehensive MLOps endeavor focused on classifying chicken diseases using advanced deep learning techniques, particularly LSTM (Long Short-Term Memory) neural networks. Leveraging Docker and DVC (Data Version Control), the pipeline is meticulously crafted to streamline the deployment and management of the deep learning model.

Features

Utilizes deep learning techniques, particularly LSTM neural networks, for image classification.

MLOps project built from scratch, incorporating best practices for machine learning model deployment and management.

Dockerized environment for reproducibility and consistency across different systems.

Pipeline automation using DVC (Data Version Control) for efficient model deployment.

User-friendly frontend for uploading images and obtaining disease classification results.

Workflow

Data Collection: Gathered a dataset comprising images of chickens affected by different diseases.

Data Preprocessing: Performed necessary preprocessing steps such as resizing, normalization, and augmentation to prepare the data for training.

Model Training: Trained LSTM neural networks on the preprocessed dataset to learn disease classification patterns.

Model Evaluation: Evaluated the trained model's performance using appropriate metrics and validation techniques.

Dockerization: Containerized the entire project using Docker to ensure portability and reproducibility.

Pipeline Creation: Utilized DVC to create a streamlined pipeline for model deployment, automating the process from training to deployment.

Frontend Development: Developed a user-friendly frontend interface allowing users to upload chicken images for disease classification.

Deployment: Deployed the trained model and frontend interface.