{"id":30895810,"url":"https://github.com/sameetasadullah/cnn-benchmark-suite","last_synced_at":"2025-09-08T22:48:07.401Z","repository":{"id":300010133,"uuid":"886086298","full_name":"SameetAsadullah/cnn-benchmark-suite","owner":"SameetAsadullah","description":"A modular deep learning evaluation framework for benchmarking multiple CNN architectures across varied optimization strategies and training configurations. Built for scalable experimentation and transferability to real-world image classification tasks.","archived":false,"fork":false,"pushed_at":"2025-06-19T11:21:46.000Z","size":825,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-19T12:29:51.164Z","etag":null,"topics":["alexnet","cifar10","cnn","computer-vision","deep-learning","googlenet","hyperparameter-tuning","image-classification","mobilenet","model-benchmarking","model-evaluation","pytorch","resnet","torchvision"],"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/SameetAsadullah.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":"2024-11-10T06:36:42.000Z","updated_at":"2025-06-19T11:55:23.000Z","dependencies_parsed_at":"2025-06-19T12:41:55.908Z","dependency_job_id":null,"html_url":"https://github.com/SameetAsadullah/cnn-benchmark-suite","commit_stats":null,"previous_names":["sameetasadullah/cnn-benchmark-suite"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SameetAsadullah/cnn-benchmark-suite","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SameetAsadullah%2Fcnn-benchmark-suite","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SameetAsadullah%2Fcnn-benchmark-suite/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SameetAsadullah%2Fcnn-benchmark-suite/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SameetAsadullah%2Fcnn-benchmark-suite/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SameetAsadullah","download_url":"https://codeload.github.com/SameetAsadullah/cnn-benchmark-suite/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SameetAsadullah%2Fcnn-benchmark-suite/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274231223,"owners_count":25245659,"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","status":"online","status_checked_at":"2025-09-08T02:00:09.813Z","response_time":121,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["alexnet","cifar10","cnn","computer-vision","deep-learning","googlenet","hyperparameter-tuning","image-classification","mobilenet","model-benchmarking","model-evaluation","pytorch","resnet","torchvision"],"created_at":"2025-09-08T22:47:49.996Z","updated_at":"2025-09-08T22:48:07.386Z","avatar_url":"https://github.com/SameetAsadullah.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🔍 Vision Model Evaluation Framework (PyTorch)\n\nA scalable framework for benchmarking deep convolutional architectures on classification tasks. This project evaluates the impact of optimizers, learning rates, and batch sizes across multiple CNN backbones — providing a reproducible experimental setup aligned with research and production best practices.\n\n---\n\n## 🚀 Key Highlights\n\n- Plug-and-play support for multiple CNN architectures\n- Scalable benchmarking with grid search over:\n  - Optimizers: `SGD`, `Adam`\n  - Learning Rates: `0.01`, `0.1`\n  - Batch Sizes: `32`, `64`\n- Data augmentation, normalization, and stratified validation split\n- Detailed metrics logging + real-time visualization support\n- Model weights saved automatically for top-performing configs\n\n---\n\n## 🧠 Architectures Supported\n\n- **Custom Lightweight CNN** (baseline)\n- **ResNet-18**\n- **MobileNetV2**\n- **GoogleNet**\n- **AlexNet** *(included for completeness; not recommended for production)*\n\n\u003e 🛡️ Modular design allows easy plug-in of ViT, EfficientNet, ConvNext, etc.\n\n---\n\n## 📊 Experiments \u0026 Logging\n\n- Validation and test performance tracked across all combinations\n- Key metrics:\n  - Train \u0026 Val Accuracy/Loss (per epoch)\n  - Best Validation Accuracy (per config)\n  - Final Test Accuracy (per model)\n- Automatic selection of best model per architecture\n- Visual analytics:\n  - Accuracy trends\n  - Impact of learning rate\n  - Batch size comparison\n  - Model vs Optimizer performance\n\n---\n\n## 🔁 Use Cases\n\n- Model architecture benchmarking\n- Optimizer sensitivity studies\n- Lightweight deployment model search\n- Academic reproducibility experiments","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsameetasadullah%2Fcnn-benchmark-suite","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsameetasadullah%2Fcnn-benchmark-suite","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsameetasadullah%2Fcnn-benchmark-suite/lists"}