{"id":34108940,"url":"https://github.com/howl-anderson/tensorweaver","last_synced_at":"2026-04-08T17:32:19.544Z","repository":{"id":286497301,"uuid":"961540509","full_name":"howl-anderson/tensorweaver","owner":"howl-anderson","description":"A modern educational deep learning framework for students, engineers and researchers","archived":false,"fork":false,"pushed_at":"2025-11-21T02:47:14.000Z","size":3432,"stargazers_count":7,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-03-17T11:19:47.984Z","etag":null,"topics":["deep-learning","deep-learning-framework","educational-project","machine-learning","machine-learning-framework"],"latest_commit_sha":null,"homepage":"https://www.tensorweaver.ai","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/howl-anderson.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-04-06T18:13:22.000Z","updated_at":"2026-03-08T10:50:08.000Z","dependencies_parsed_at":"2025-04-06T20:48:55.615Z","dependency_job_id":"edcb7cba-75db-49c2-9245-3729c1556992","html_url":"https://github.com/howl-anderson/tensorweaver","commit_stats":null,"previous_names":["howl-anderson/tensorweaver"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/howl-anderson/tensorweaver","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/howl-anderson%2Ftensorweaver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/howl-anderson%2Ftensorweaver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/howl-anderson%2Ftensorweaver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/howl-anderson%2Ftensorweaver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/howl-anderson","download_url":"https://codeload.github.com/howl-anderson/tensorweaver/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/howl-anderson%2Ftensorweaver/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31566824,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T14:31:17.711Z","status":"ssl_error","status_checked_at":"2026-04-08T14:31:17.202Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["deep-learning","deep-learning-framework","educational-project","machine-learning","machine-learning-framework"],"created_at":"2025-12-14T18:24:11.879Z","updated_at":"2026-04-08T17:32:19.533Z","avatar_url":"https://github.com/howl-anderson.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TensorWeaver\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/assets/logo.png\" alt=\"TensorWeaver Logo\" width=\"200\"/\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003e🧠 A transparent, debuggable deep learning framework\u003c/strong\u003e\u003cbr\u003e\n  \u003cem\u003ePyTorch-compatible implementation with full visibility into internals\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://pypi.org/project/tensorweaver/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/tensorweaver.svg\" alt=\"PyPI version\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/howl-anderson/tensorweaver/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-blue.svg\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/howl-anderson/tensorweaver/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/howl-anderson/tensorweaver.svg\" alt=\"GitHub stars\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.tensorweaver.ai\"\u003e\u003cimg src=\"https://img.shields.io/badge/docs-tensorweaver.ai-blue\" alt=\"Documentation\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## 🤔 **Ever feel like PyTorch is a black box?**\n\n```python\n# What's actually happening here? 🤷‍♂️\nloss.backward()  # Magic? \noptimizer.step()  # More magic?\n```\n\n**You're not alone.** Most ML students and engineers use deep learning frameworks without understanding the internals. That's where TensorWeaver comes in.\n\n## 🎯 **What is TensorWeaver?**\n\nTensorWeaver is a **transparent deep learning framework** that reveals exactly how PyTorch works under the hood. Built from scratch in pure Python, it provides complete visibility into automatic differentiation, neural networks, and optimization algorithms.\n\n\u003e **Think of it as \"PyTorch with full transparency\"** 🔧\n\n### **🎓 Perfect for:**\n- **ML Engineers** debugging complex gradient issues and understanding framework internals\n- **Researchers** who need full control over their implementations\n- **Software Engineers** building custom deep learning solutions\n- **Technical Teams** who need to understand and modify framework behavior\n- **Developers** who refuse to accept \"black box\" solutions\n\n\u003e **💡 Pro Tip**: Use `import tensorweaver as torch` for seamless PyTorch compatibility!\n\n## ⚡ **Quick Start - See the Magic Yourself**\n\n```bash\npip install tensorweaver\n```\n\n```python\nimport tensorweaver as torch  # PyTorch-compatible API!\n\n# 1. Prepare Data (y = 2x)\nx = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\ny = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n\n# 2. Define Model\nmodel = torch.nn.Linear(1, 1)\n\n# 3. Train\noptimizer = torch.optim.SGD(model.parameters(), lr=0.01)\ncriterion = torch.nn.MSELoss()\n\nprint(\"Training...\")\nfor epoch in range(100):\n    # Forward\n    y_pred = model(x)\n    loss = criterion(y_pred, y)\n    \n    # Backward\n    optimizer.zero_grad()\n    loss.backward()\n    optimizer.step()\n    \n    if epoch % 20 == 0:\n        print(f\"Epoch {epoch}: Loss = {loss.item():.4f}\")\n\n# 4. Result\n# The difference? You can see EXACTLY what happens inside! 👀\nprint(f\"\\nPrediction for x=5.0: {model(torch.tensor([[5.0]])).item():.4f} (Expected: 10.0)\")\n```\n\n🚀 **[Try it live in your browser →](https://mybinder.org/v2/gh/howl-anderson/tensorweaver/HEAD?urlpath=%2Fdoc%2Ftree%2Fmilestones%2F01_linear_regression%2Fdemo.ipynb)**\n\n## 🧠 **What You'll Learn**\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n### **🔬 Deep Learning Internals**\n- How automatic differentiation works\n- Backpropagation step-by-step\n- Computational graph construction\n- Gradient computation and flow\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n### **🛠️ Framework Design**\n- Tensor operations implementation\n- Neural network architecture\n- Optimizer algorithms\n- Model export (ONNX) mechanisms\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## 💎 **Why TensorWeaver?**\n\n| 🏭 **Production Frameworks** | 🔬 **TensorWeaver** |\n|------------------------------|---------------------|\n| ❌ Complex C++ codebase | ✅ Pure Python - fully debuggable |\n| ❌ Optimized for speed only | ✅ Optimized for understanding and modification |\n| ❌ \"Trust us, it works\" | ✅ \"Here's exactly how it works\" |\n| ❌ Black box internals | ✅ Complete transparency and control |\n\n### **🚀 Key Features**\n\n- **🔍 Transparent Implementation**: Every operation is visible, debuggable, and modifiable\n- **🐍 Pure Python**: No hidden C++ complexity - full control over the codebase\n- **🎯 PyTorch-Compatible API**: Drop-in replacement with complete visibility\n- **🛠️ Engineering Excellence**: Clean architecture designed for understanding and extension\n- **🧪 Complete Functionality**: Autodiff, neural networks, optimizers, ONNX export\n- **📊 Production Ready**: Export trained models to ONNX for deployment\n\n## 🗺️ **Technical Roadmap**\n\n### **🔧 Core Components**\n1. **[Tensor Operations](milestones/01_linear_regression/)** - Fundamental tensor mechanics and operations\n2. **[Linear Models](milestones/01_linear_regression/demo.ipynb)** - Basic neural network implementation\n3. **Automatic Differentiation** - Gradient computation engine *(coming soon)*\n\n### **🏗️ Advanced Architecture**\n4. **[Deep Networks](milestones/03_multilayer_perceptron/)** - Multi-layer perceptron and complex architectures\n5. **Optimization Algorithms** - Advanced training techniques *(coming soon)*\n6. **[Model Deployment](milestones/02_onnx_export/)** - ONNX export for production systems\n\n### **⚡ Performance \u0026 Extensions**\n7. **Custom Operators** - Framework extension capabilities *(coming soon)*\n8. **Performance Engineering** - Optimization techniques *(coming soon)*\n9. **Hardware Acceleration** - GPU computation support *(in development)*\n\n\u003e **📝 Note**: Some documentation links are still in development. Check our [milestones](milestones/) for working examples!\n\n\n\n## 🚀 **Get Started Now**\n\n### **📦 Installation**\n```bash\n# Option 1: Install from PyPI (recommended)\npip install tensorweaver\n\n# Option 2: Install from source (for contributors)\ngit clone https://github.com/howl-anderson/tensorweaver.git\ncd tensorweaver\nuv sync --group dev\n```\n\n### **🎯 Quick Start Guide**\n\n1. **[📂 Browse Examples](milestones/)** - Working implementations and demos\n2. **[🚀 Try Online](https://mybinder.org/v2/gh/howl-anderson/tensorweaver/HEAD)** - Browser-based environment\n3. **[💬 Community Forum](https://github.com/howl-anderson/tensorweaver/discussions)** - Technical discussions and support\n4. **[📖 Documentation](https://tensorweaver.ai)** - Complete API reference *(expanding)*\n\n## 🤝 **Contributing**\n\nTensorWeaver thrives on community contributions! Whether you're:\n- 🐛 **Reporting bugs**\n- 💡 **Suggesting features** \n- 📖 **Improving documentation**\n- 🧪 **Adding examples**\n- 🔧 **Writing code**\n\nWe welcome you! Please open an issue or submit a pull request - contribution guidelines coming soon!\n\n## 📚 **Resources**\n\n- **📖 [Documentation](https://tensorweaver.ai)** - Framework overview\n- **💬 [Discussions](https://github.com/howl-anderson/tensorweaver/discussions)** - Community Q\u0026A\n- **🐛 [Issues](https://github.com/howl-anderson/tensorweaver/issues)** - Bug reports and feature requests\n- **📧 [Follow Updates](https://github.com/howl-anderson/tensorweaver)** - Star/watch for latest changes\n\n\n## ⭐ **Why Stars Matter**\n\nIf TensorWeaver helped you debug, understand, or build better models, please consider starring the repository! It helps other engineers discover this transparent framework.\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/howl-anderson/tensorweaver/stargazers\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/stars/howl-anderson/tensorweaver?style=social\" alt=\"GitHub stars\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n## 📄 **License**\n\nTensorWeaver is MIT licensed. See [LICENSE](LICENSE) for details.\n\n## 🙏 **Acknowledgments**\n\n- Inspired by transparent implementations: **Micrograd**, **TinyFlow**, and **DeZero**\n- Thanks to the PyTorch team for the elegant API design\n- Grateful to all contributors and the open-source community\n\n---\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eReady for complete transparency in deep learning?\u003c/strong\u003e\u003cbr\u003e\n  \u003ca href=\"https://tensorweaver.ai\"\u003e🚀 Explore TensorWeaver at tensorweaver.ai\u003c/a\u003e\n\u003c/p\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhowl-anderson%2Ftensorweaver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhowl-anderson%2Ftensorweaver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhowl-anderson%2Ftensorweaver/lists"}