{"id":15118556,"url":"https://github.com/onlydole/pytorch-keynote-2024","last_synced_at":"2026-01-20T03:01:29.250Z","repository":{"id":257495832,"uuid":"858448991","full_name":"onlydole/pytorch-keynote-2024","owner":"onlydole","description":"PyTorch-powered app that turns images into music. Upload a pic, get a unique electronic composition.","archived":false,"fork":false,"pushed_at":"2024-09-17T01:56:11.000Z","size":7480,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-13T02:51:17.602Z","etag":null,"topics":["ai","genai","kubernetes","pytorch"],"latest_commit_sha":null,"homepage":"https://cncf.io","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/onlydole.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":"2024-09-16T23:06:21.000Z","updated_at":"2024-09-18T20:49:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"9b6d7413-e218-4a10-b447-1983aaf3170d","html_url":"https://github.com/onlydole/pytorch-keynote-2024","commit_stats":null,"previous_names":["onlydole/pytorch-keynote-2024"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/onlydole/pytorch-keynote-2024","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/onlydole%2Fpytorch-keynote-2024","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/onlydole%2Fpytorch-keynote-2024/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/onlydole%2Fpytorch-keynote-2024/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/onlydole%2Fpytorch-keynote-2024/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/onlydole","download_url":"https://codeload.github.com/onlydole/pytorch-keynote-2024/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/onlydole%2Fpytorch-keynote-2024/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28594958,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-20T02:08:49.799Z","status":"ssl_error","status_checked_at":"2026-01-20T02:08:44.148Z","response_time":117,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["ai","genai","kubernetes","pytorch"],"created_at":"2024-09-26T01:46:58.329Z","updated_at":"2026-01-20T03:01:29.026Z","avatar_url":"https://github.com/onlydole.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PyTorch Keynote 2024 Demo\n\n[![CI](https://github.com/onlydole/pytorch-keynote-2024/actions/workflows/build.yml/badge.svg)](https://github.com/onlydole/pytorch-keynote-2024/actions/workflows/build.yml)\n[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n\n## Overview\n\nThis project is a unique demonstration of PyTorch's capabilities, created for the PyTorch Conference 2024.\nIt combines computer vision and audio synthesis to generate melodic sounds based on input images.\nThe application uses a PyTorch neural network to analyze images and extract features, which are then used to create varied, electronic-style music.\nThis cloud native, open source project showcases the power of machine learning in creative applications.\n\n## Features\n\n- Upload any image and receive a unique musical composition based on that image\n- PyTorch-powered image analysis using a custom CNN model\n- Dynamic music generation influenced by image features\n- Web-based interface for easy interaction\n- Dockerized application for simple deployment and scalability\n- Kubernetes configuration for cloud native deployment\n\n## Tech Stack\n\n- Frontend: React with Tailwind CSS for styling\n- Backend: Flask with Flask-CORS for API\n- ML Framework: PyTorch for image analysis\n- Audio Processing: NumPy and SciPy for sound generation\n- Image Processing: Pillow (PIL) for image handling\n- Containerization: Docker and Docker Compose\n- Orchestration: Kubernetes\n\n## Prerequisites\n\n- Docker and Docker Compose for local development\n- Kubernetes cluster for cloud deployment (Kind can be used for local Kubernetes development)\n\n## Getting Started\n\n### Local Development\n\n1. Clone the repository:\n\n   ```sh\n   git clone https://github.com/onlydole/pytorch-keynote-2024.git\n   cd pytorch-keynote-2024\n   ```\n\n2. Build and run the Docker container:\n\n   ```sh\n   docker compose up --build\n   ```\n\n3. Open your web browser and navigate to `http://localhost:8080`\n\n### Kubernetes Deployment\n\n1. If you don't have a Kubernetes cluster, you can use [Kind](https://kind.sigs.k8s.io/) to create one locally:\n\n   ```sh\n   kind create cluster --config cluster.yml\n   ```\n\n2. Apply the Kubernetes configurations:\n\n   ```sh\n   kubectl apply -f kubernetes/\n   ```\n\n3. Access the application:\n   - For Kind: Use port forwarding to access the service\n\n     ```sh\n     kubectl port-forward service/pytorch-music-service 8080:8080\n     ```\n\n4. Open your web browser and navigate to `http://localhost:8080`\n\n## How It Works\n\n1. The user uploads an image through the React-based web interface.\n2. The image is sent to the Flask backend.\n3. The image is processed by a custom PyTorch CNN, extracting various features.\n4. These features influence different aspects of music generation.\n5. The backend generates a unique audio clip.\n6. The generated audio is sent back to the user's browser for playback.\n\n## Scripts\n\n- `startup.sh`: Script to start the application\n- `shutdown.sh`: Script to shut down the application\n\n## Contributing\n\nWe welcome contributions! Please feel free to submit a Pull Request.\n\n## CI/CD\n\nThis project uses GitHub Actions for building and publishing the container image. You can view the latest run status using the badges at the top of this README.\n\n## License\n\nThis project is licensed under the Apache License 2.0. See the [LICENSE](LICENSE) file for details.\n\n## Acknowledgments\n\n- PyTorch team for their powerful deep learning framework\n- Flask team for the lightweight web framework\n- React team for the frontend library\n- The open source community for various tools and libraries used in this project\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fonlydole%2Fpytorch-keynote-2024","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fonlydole%2Fpytorch-keynote-2024","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fonlydole%2Fpytorch-keynote-2024/lists"}