{"id":19765910,"url":"https://github.com/themihirmathur/kiddis","last_synced_at":"2026-04-10T04:58:07.552Z","repository":{"id":245277980,"uuid":"817769931","full_name":"themihirmathur/Kiddis","owner":"themihirmathur","description":"This project leverages deep learning for the classification of kidney disease using a combination of MLflow and DVC for experiment tracking, versioning, and orchestration.","archived":false,"fork":false,"pushed_at":"2024-09-04T16:31:57.000Z","size":53887,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-11T00:12:51.569Z","etag":null,"topics":["aws-ec2","aws-s3","ci-cd-pipeline","docker","dvc-pipeline","keras","mlflow","mlops","python","tensorflow"],"latest_commit_sha":null,"homepage":"https://github.com/themihirmathur/Kiddis","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/themihirmathur.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-20T12:02:23.000Z","updated_at":"2024-09-04T16:32:02.000Z","dependencies_parsed_at":"2024-09-05T22:28:14.709Z","dependency_job_id":null,"html_url":"https://github.com/themihirmathur/Kiddis","commit_stats":null,"previous_names":["themihirmathur/kiddis"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themihirmathur%2FKiddis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themihirmathur%2FKiddis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themihirmathur%2FKiddis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themihirmathur%2FKiddis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/themihirmathur","download_url":"https://codeload.github.com/themihirmathur/Kiddis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241099524,"owners_count":19909568,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aws-ec2","aws-s3","ci-cd-pipeline","docker","dvc-pipeline","keras","mlflow","mlops","python","tensorflow"],"created_at":"2024-11-12T04:20:25.931Z","updated_at":"2025-12-30T21:07:32.996Z","avatar_url":"https://github.com/themihirmathur.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kiddis - Kidney Disease Classification with MLflow and DVC \r\n\r\nThis project leverages deep learning for the classification of kidney disease using a combination of MLflow and DVC for experiment tracking, versioning, and orchestration. The project encompasses a structured workflow, facilitating both experimentation and production-grade deployment.\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n\r\n![image](https://github.com/themihirmathur/Kiddis/assets/92594107/259ebb73-f060-4864-8b34-ed188e67a50e)\r\n\r\n## Workflows\r\n\r\n### Configuration Files\r\n- **config.yaml**: General configuration settings.\r\n- **secrets.yaml**: Optional file for sensitive information.\r\n- **params.yaml**: Parameters for model training and evaluation.\r\n\r\n### Source Code Updates\r\n1. Update the entity definitions.\r\n2. Enhance the configuration manager in the `src` config directory.\r\n3. Revise the components for improved functionality.\r\n4. Update the pipeline to reflect changes.\r\n5. Modify `main.py` to incorporate new logic.\r\n6. Amend `dvc.yaml` for Data Version Control.\r\n\r\n### Application Entry Point\r\n- `app.py`: Main application file to run the project.\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n\r\n## Running the Project\r\n\r\n### Clone the Repository\r\n```sh\r\ngit clone https://github.com/themihirmathur/Kiddis.git\r\ncd Kiddis\r\n```\r\n\r\n### Create and Activate Conda Environment\r\n```sh\r\nconda create -n cnncls python=3.8 -y\r\nconda activate cnncls\r\n```\r\n\r\n### Install Requirements\r\n```sh\r\npip install -r requirements.txt\r\n```\r\n\r\n### Run the Application\r\n```sh\r\npython app.py\r\n```\r\nNow, open your local host and port to access the application.\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n\r\n## MLflow Integration\r\n\r\nMLflow is used to track experiments, log models, and facilitate model deployment.\r\n\r\n### Starting MLflow UI\r\n```sh\r\nmlflow ui\r\n```\r\n\r\n### Setting up MLflow with DagsHub\r\n```sh\r\nexport MLFLOW_TRACKING_URI=https://dagshub.com/entbappy/Kiddis.mlflow\r\nexport MLFLOW_TRACKING_USERNAME=entbappy \r\nexport MLFLOW_TRACKING_PASSWORD=6824692c47a369aa6f9eac5b10041d5c8edbcef0\r\npython script.py\r\n```\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n\r\n## DVC Commands\r\n\r\nDVC is utilized for lightweight experiment tracking and pipeline orchestration.\r\n\r\n### Initialize DVC\r\n```sh\r\ndvc init\r\n```\r\n\r\n### Reproduce DVC Pipeline\r\n```sh\r\ndvc repro\r\n```\r\n\r\n### Visualize DVC Pipeline\r\n```sh\r\ndvc dag\r\n```\r\n\r\n\r\n## About MLflow \u0026 DVC\r\n\r\n### MLflow\r\n- **Production Grade**: Suitable for production environments.\r\n- **Experiment Tracking**: Logs and tags models and experiments.\r\n\r\n### DVC\r\n- **Lightweight**: Ideal for proof-of-concept projects.\r\n- **Experiment Tracker**: Manages and tracks experiments.\r\n- **Pipeline Orchestration**: Enables creation and management of pipelines.\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n\r\n## AWS CI/CD Deployment with GitHub Actions\r\n\r\nThis section describes the steps to deploy the application using AWS services and GitHub Actions for continuous integration and continuous deployment.\r\n\r\n### Steps to Deploy\r\n\r\n1. **Login to AWS Console**: Access your AWS management console.\r\n2. **Create IAM User for Deployment**: Assign specific access permissions:\r\n   - EC2 Access\r\n   - ECR Access\r\n\r\n### Deployment Description\r\n1. **Build Docker Image**: Create a Docker image of the source code.\r\n2. **Push Docker Image to ECR**: Store the Docker image in AWS Elastic Container Registry (ECR).\r\n3. **Launch EC2 Instance**: Create an EC2 instance to host the application.\r\n4. **Pull Docker Image from ECR**: Retrieve the Docker image from ECR in the EC2 instance.\r\n5. **Run Docker Image in EC2**: Deploy and run the Docker container in the EC2 instance.\r\n\r\n### IAM Policies Required\r\n- `AmazonEC2ContainerRegistryFullAccess`\r\n- `AmazonEC2FullAccess`\r\n\r\n### Create ECR Repository\r\n```sh\r\naws ecr create-repository --repository-name kidney-disease-classification\r\n```\r\n\r\n### Create EC2 Instance\r\n1. **Launch EC2 Instance (Ubuntu)**\r\n2. **Install Docker on EC2**\r\n   ```sh\r\n   sudo apt-get update -y\r\n   sudo apt-get upgrade\r\n   curl -fsSL https://get.docker.com -o get-docker.sh\r\n   sudo sh get-docker.sh\r\n   sudo usermod -aG docker ubuntu\r\n   newgrp docker\r\n   ```\r\n\r\n### Configure EC2 as Self-Hosted Runner\r\n1. Go to `Settings \u003e Actions \u003e Runners` in GitHub.\r\n2. Add a new self-hosted runner and follow the instructions to configure it.\r\n\r\n### Setup GitHub Secrets\r\n```sh\r\nAWS_ACCESS_KEY_ID=\u003cyour_aws_access_key_id\u003e\r\nAWS_SECRET_ACCESS_KEY=\u003cyour_aws_secret_access_key\u003e\r\nAWS_REGION=us-east-1\r\nAWS_ECR_LOGIN_URI=566373416292.dkr.ecr.us-east-1.amazonaws.com\r\nECR_REPOSITORY_NAME=kidney-disease-classification\r\n```\r\n\r\n---\r\n\r\nThis project demonstrates a comprehensive approach to developing, experimenting, and deploying a deep learning model for kidney disease classification using modern MLOps tools and practices.\r\n\r\n\u003cp align=\"left\"\u003e\r\n  \u003cimg src=\"https://www.animatedimages.org/data/media/562/animated-line-image-0184.gif\" width=\"1920\" \r\n\u003c/p\u003e\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthemihirmathur%2Fkiddis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthemihirmathur%2Fkiddis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthemihirmathur%2Fkiddis/lists"}