{"id":33374388,"url":"https://github.com/supershivam07/vision-ai","last_synced_at":"2026-04-07T20:31:37.038Z","repository":{"id":310525114,"uuid":"1037550534","full_name":"Supershivam07/Vision-AI","owner":"Supershivam07","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-18T17:15:56.000Z","size":57885,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-18T18:12:01.594Z","etag":null,"topics":["cifar10","cnn","confusion-matrix","dataset","evaluation","fine-tuning","inference","jyputer-notebook","keras","mobilenetv2","model","prediction","preprocessing","python","tensorflow","tensorflow2","training","transfer-learning","vision-ai","weights"],"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/Supershivam07.png","metadata":{"files":{"readme":"README.md","changelog":"history_basic_cnn.png","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":"2025-08-13T18:38:56.000Z","updated_at":"2025-08-18T17:32:56.000Z","dependencies_parsed_at":"2025-08-18T18:22:06.114Z","dependency_job_id":null,"html_url":"https://github.com/Supershivam07/Vision-AI","commit_stats":null,"previous_names":["supershivam07/image-recognization"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Supershivam07/Vision-AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Supershivam07%2FVision-AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Supershivam07%2FVision-AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Supershivam07%2FVision-AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Supershivam07%2FVision-AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Supershivam07","download_url":"https://codeload.github.com/Supershivam07/Vision-AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Supershivam07%2FVision-AI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":285873538,"owners_count":27246054,"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":"2025-11-22T02:00:05.934Z","response_time":64,"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":["cifar10","cnn","confusion-matrix","dataset","evaluation","fine-tuning","inference","jyputer-notebook","keras","mobilenetv2","model","prediction","preprocessing","python","tensorflow","tensorflow2","training","transfer-learning","vision-ai","weights"],"created_at":"2025-11-22T23:01:16.627Z","updated_at":"2025-11-22T23:01:21.889Z","avatar_url":"https://github.com/Supershivam07.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Vision AI in 5 Days – CIFAR-10\n\nThis repo is a complete starter to build, evaluate, and demo an image-classification system in **Python + TensorFlow/Keras**. It follows the bootcamp flow: preprocess → train basic CNN → evaluate → transfer learning → fine-tune → demo → publish.\n\n## Quickstart (Google Colab recommended)\n\n1. **Upload this zip** to Colab and unzip:\n```bash\n!unzip vision_ai_cifar10_project.zip -d /content/\n%cd /content/vision_ai_cifar10_project\n```\n\n2. **(Optional) Preprocess \u0026 cache data:**\n```bash\n!python src/preprocess.py\n```\n\n3. **Train a basic CNN** (saves model \u0026 plots):\n```bash\n!python src/train_cnn.py\n```\n\n4. **Evaluate saved model** (confusion matrix + report):\n```bash\n!python src/evaluate.py --model models/basic_cnn.h5 --prefix basic_cnn\n```\n\n5. **Transfer learning (MobileNetV2)**:\n```bash\n!python src/train_transfer.py\n!python src/evaluate.py --model models/mobilenetv2_cifar10.h5 --prefix mobilenetv2\n```\n\n6. **Single-image inference**:\n```bash\n# Replace with your image path\n!python src/infer.py --model models/mobilenetv2_cifar10.h5 --image sample.jpg\n```\n\n## Repo Layout\n```\nvision_ai_cifar10_project/\n  ├─ data/               # cached dataset (created automatically)\n  ├─ docs/               # slides, LinkedIn post, demo script templates\n  ├─ models/             # trained .h5 models\n  ├─ outputs/            # plots, confusion matrices, reports\n  └─ src/                # all Python code\n```\n\n## Notes\n- Default dataset: **CIFAR-10** (built into Keras). You can swap to **Cats vs Dogs** via `tensorflow_datasets` with small changes.\n- Training uses **GPU** if available. In Colab: Runtime → Change runtime type → GPU.\n- For fast submission, you can reduce epochs in the training scripts.\n\nGood luck! 🚀\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupershivam07%2Fvision-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsupershivam07%2Fvision-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupershivam07%2Fvision-ai/lists"}