{"id":27979398,"url":"https://github.com/reneking-tech/cifar10-lightning","last_synced_at":"2026-05-07T18:34:10.828Z","repository":{"id":291755657,"uuid":"978669593","full_name":"reneking-tech/cifar10-lightning","owner":"reneking-tech","description":"Hands-on deep learning with PyTorch \u0026 Lightning — CIFAR-10 classification","archived":false,"fork":false,"pushed_at":"2025-05-06T12:43:01.000Z","size":115,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-08T02:52:53.168Z","etag":null,"topics":["ai","cifar10","cnn","deep-learning","image-classification","machine-learning","ml-engineering","model-evaluation","notebooks","python","pytorch","pytorch-lightning","transfer-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/reneking-tech.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-05-06T10:40:17.000Z","updated_at":"2025-05-06T12:43:05.000Z","dependencies_parsed_at":"2025-05-08T02:52:54.394Z","dependency_job_id":"0571202b-feee-4c6a-b27b-ddc0afb13ae6","html_url":"https://github.com/reneking-tech/cifar10-lightning","commit_stats":null,"previous_names":["reneking-tech/cifar10-lightning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/reneking-tech/cifar10-lightning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reneking-tech%2Fcifar10-lightning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reneking-tech%2Fcifar10-lightning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reneking-tech%2Fcifar10-lightning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reneking-tech%2Fcifar10-lightning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reneking-tech","download_url":"https://codeload.github.com/reneking-tech/cifar10-lightning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reneking-tech%2Fcifar10-lightning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32750697,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["ai","cifar10","cnn","deep-learning","image-classification","machine-learning","ml-engineering","model-evaluation","notebooks","python","pytorch","pytorch-lightning","transfer-learning"],"created_at":"2025-05-08T02:52:50.164Z","updated_at":"2026-05-07T18:34:10.813Z","avatar_url":"https://github.com/reneking-tech.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 CIFAR-10 Classifier: From PyTorch to Lightning\n\nThis project demonstrates how to build and train a simple Convolutional Neural Network (CNN) on the CIFAR-10 image classification dataset using both **vanilla PyTorch** and **PyTorch Lightning**.\n\nIt was created as a practical, hands-on learning journey after completing Andrew Ng's Machine Learning Specialization. The goal: go from foundational ML understanding to real model implementation and training.\n\n---\n\n## 🚀 What’s Inside\n\n- ✅ CIFAR-10 data loading with torchvision\n- 🧱 CNN architecture (`SimpleCNN`)\n- 🔁 Custom training + validation loops\n- ⚡ PyTorch Lightning module (`LitCNN`)\n- 📈 Loss/accuracy visualization\n- 💡 Reflections on overfitting + improvements\n- ✅ Pre-commit auto-formatting, notebook cleaning, code linting\n\n---\n\n## 📊 Training Results\n\n### Vanilla PyTorch (5 Epochs)\n\n- Final **Train Acc:** ~98%\n- Final **Val Acc:** ~71%\n- ❗ Validation loss increased → signs of **overfitting**\n\n### PyTorch Lightning (5 Epochs)\n\n- Final **Val Loss:** ~0.83\n- Final **Val Accuracy:** ~71.2%\n\n\u003e 🔍 Same accuracy, but Lightning yielded a cleaner validation curve and easier setup.\n\n---\n\n## 🖼️ Training Curves\n\n### 🔽 Loss\n\n![Training vs Validation Loss](notebooks/images/loss_plot.png)\n\n### 🔼 Accuracy\n\n![Training vs Validation Accuracy](notebooks/images/accuracy_plot.png)\n\n\u003e _Outputs were stripped using pre-commit to keep this repo clean._\n\n---\n\n## 🧠 Reflections\n\nDespite strong training performance, the validation metrics suggest overfitting. This provides a clear path to improvement:\n\n- ✅ Add dropout layers\n- ✅ Use weight decay\n- ✅ Apply data augmentation (`RandomCrop`, `HorizontalFlip`)\n- ✅ Explore more expressive architectures or learning rate schedulers\n\n---\n\n## ✅ Pre-Commit Enabled\n\n![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?style=flat-square\u0026logo=pre-commit)\n\nThis project uses [`pre-commit`](https://pre-commit.com/) to ensure:\n- Clean `.ipynb` notebooks (`nbstripout`)\n- Consistent code style (`black`, `isort`)\n- Valid YAML + JSON\n- No trailing whitespace or newline issues\n\nTo install:\n\n```bash\npip install pre-commit\npre-commit install\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freneking-tech%2Fcifar10-lightning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freneking-tech%2Fcifar10-lightning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freneking-tech%2Fcifar10-lightning/lists"}