{"id":33374372,"url":"https://github.com/ramirezramiro/onnx-fastapi","last_synced_at":"2026-04-13T04:03:12.461Z","repository":{"id":317527600,"uuid":"1064696226","full_name":"ramirezramiro/onnx-fastapi","owner":"ramirezramiro","description":"Starter kit for ONNX models: predictable CPU performance, simple REST, fast to demo","archived":false,"fork":false,"pushed_at":"2025-10-01T12:30:27.000Z","size":9200,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-22T23:03:10.308Z","etag":null,"topics":["computer-vision","cpu","docker","fastapi","inference","onnx","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/ramirezramiro.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-26T12:18:43.000Z","updated_at":"2025-10-01T12:30:30.000Z","dependencies_parsed_at":"2025-10-01T14:22:48.953Z","dependency_job_id":"8b5caad0-82a8-4dc5-8ab4-6e54c2c1aaad","html_url":"https://github.com/ramirezramiro/onnx-fastapi","commit_stats":null,"previous_names":["ramirezramiro/onnx-fastapi"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ramirezramiro/onnx-fastapi","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramirezramiro%2Fonnx-fastapi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramirezramiro%2Fonnx-fastapi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramirezramiro%2Fonnx-fastapi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramirezramiro%2Fonnx-fastapi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ramirezramiro","download_url":"https://codeload.github.com/ramirezramiro/onnx-fastapi/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramirezramiro%2Fonnx-fastapi/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31739050,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T03:27:07.512Z","status":"ssl_error","status_checked_at":"2026-04-13T03:26:53.610Z","response_time":93,"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":["computer-vision","cpu","docker","fastapi","inference","onnx","python"],"created_at":"2025-11-22T23:01:04.717Z","updated_at":"2026-04-13T04:03:12.415Z","avatar_url":"https://github.com/ramirezramiro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"**Prerequisites**\nWSL 2 (Windows Subsystem for Linux) → install from Microsoft Store:\nhttps://apps.microsoft.com/detail/9p9tqf7mrm4r?hl=en-US\u0026gl=TW\n\n**CPU-optimized inference (ONNX Runtime)**\nModel: MobileNetV3-Small (ImageNet)\nHardware: Colab CPU\nLatency (avg): ~4.23 ms/img\nThroughput: ~236.27 FPS\nExport: PyTorch → ONNX (opset 13, dynamic batch), ORT graph optimizations ON\n\n# onnx-fastapi (CPU)\n\nMinimal FastAPI service for ONNX inference on CPU (MobileNetV3-Small example).\n\n## Run and Build (Docker)\n```bash\ndocker build -t onnx-fastapi:cpu .\ndocker run --rm -p 8000:8000 onnx-fastapi:cpu\n# open http://localhost:8000/docs\n```\n\n## API Health check\n```bash\ncurl http://localhost:8000/health\n# {\"status\":\"ok\"}\n```\n\n## Prediction\n```bash\n# Replace with your image path\ncurl -X POST \"http://localhost:8000/predict\" \\\n  -H \"accept: application/json\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F \"file=@samples/cat.jpg\"\n```\n## Prediction\n```json\n{\n  \"top1\": {\"label\": \"tabby_cat\", \"prob\": 0.87},\n  \"top5\": [\n    {\"label\": \"tabby_cat\", \"prob\": 0.87},\n    {\"label\": \"tiger_cat\", \"prob\": 0.07},\n    {\"label\": \"Egyptian_cat\", \"prob\": 0.03},\n    {\"label\": \"lynx\", \"prob\": 0.02},\n    {\"label\": \"cougar\", \"prob\": 0.01}\n  ]\n}\n```\n\n## Architecture Diagram\n```mermaid\nflowchart LR\n  A[Client / cURL / App] --\u003e|HTTP: /predict| B[FastAPI Service]\n  B --\u003e|NumPy tensors| C[ONNX Runtime]\n  C --\u003e|CPU| D[(model.onnx)]\n\n  subgraph DockerContainer[\"Docker Container\"]\n    B\n    C\n    D\n  end\n\n  E[(Host FS)]\n  D --\u003e|\"bind-mount (optional)\"| E\n```\n\n\n## Final takeaway \n\nFastAPI exposes /health and /predict.\n\nONNX Runtime (CPU) runs inference—no GPU required.\n\nModel can be baked into the image or bind-mounted at runtime for quick swaps.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framirezramiro%2Fonnx-fastapi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Framirezramiro%2Fonnx-fastapi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framirezramiro%2Fonnx-fastapi/lists"}