{"id":16193705,"url":"https://github.com/cyyeh/dog-breed-classifier-project","last_synced_at":"2026-02-14T17:03:48.203Z","repository":{"id":43513088,"uuid":"270186454","full_name":"cyyeh/dog-breed-classifier-project","owner":"cyyeh","description":"Udacity Machine Learning Engineer Nanodegree Capstone Project","archived":false,"fork":false,"pushed_at":"2023-01-06T08:41:34.000Z","size":62273,"stargazers_count":3,"open_issues_count":24,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-05T06:39:25.941Z","etag":null,"topics":["computer-vision","deep-learning","fastapi","gcp-cloud-run","mobilenetv2","python3","pytorch","webapp"],"latest_commit_sha":null,"homepage":"https://dog-breed-classifier.netlify.app/","language":"JavaScript","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/cyyeh.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}},"created_at":"2020-06-07T04:02:38.000Z","updated_at":"2022-11-13T13:46:07.000Z","dependencies_parsed_at":"2023-02-05T17:46:49.304Z","dependency_job_id":null,"html_url":"https://github.com/cyyeh/dog-breed-classifier-project","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cyyeh/dog-breed-classifier-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyyeh%2Fdog-breed-classifier-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyyeh%2Fdog-breed-classifier-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyyeh%2Fdog-breed-classifier-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyyeh%2Fdog-breed-classifier-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cyyeh","download_url":"https://codeload.github.com/cyyeh/dog-breed-classifier-project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cyyeh%2Fdog-breed-classifier-project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29450608,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-14T15:52:44.973Z","status":"ssl_error","status_checked_at":"2026-02-14T15:52:11.208Z","response_time":53,"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":["computer-vision","deep-learning","fastapi","gcp-cloud-run","mobilenetv2","python3","pytorch","webapp"],"created_at":"2024-10-10T08:16:17.962Z","updated_at":"2026-02-14T17:03:48.177Z","avatar_url":"https://github.com/cyyeh.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dog Breed Classification Project\n\n![Visualization of the codebase](./diagram.svg)\n\n## Project Functionalities\n\n- Users can know more about dog breeds and their information through taking photos or uploading photos.\n- Users can also directly use photos provided by the project to quickly play around.\n- Users can get top 3 dog breed prediction results with wikipedia links.\n- Users can learn English and Chinese at the same time.\n\n## System Architecture\n\n![](system-diagram.png)\n\n- dog detection\n  - model: MobileNet V2 pretrained model without finetuning\n  - input: an image having RGB channels with Base64 encoding\n  - output: boolean\n- dog classification\n  - model: MobileNet V2 pretrained model with finetuning\n  - input: an image having RGB channels with Base64 encoding\n  - output: top-3 prediction results(dog breed names and prediction probabilities)\n\n## Project Structure\n\n- api: backend\n- web: frontend\n\n## Used Tools/Technologies\n\n- frontend\n  - HTML/CSS/JavaScript\n  - Materialize\n  - Babel\n  - Webpack\n- backend\n  - Python\n    - FastAPI\n  - Docker\n  - GCP\n    - Cloud Run\n- deep learning\n  - PyTorch\n\n## Deep Learning Under the Hood in This Project\n\nYou can check [this repo](https://github.com/cyyeh/ml-engineering-ndegree/tree/master/projects/capstone-project) for further details, and this project is orginally from my Udacity Machine Learning Engineer Nanodegree capstone project. However, I have changed some model details for this dog breed classifier, you can check [here](https://github.com/cyyeh/ml-engineering-ndegree/tree/master/projects/capstone-project/deployment) for more details.\n\n## Setup\n\n### Frontend\n\n\u003e please see the web folder\n- `npm install` (download dependencies first)\n- local development\n  - `npm run start`\n- deployment\n  - `npm run build`\n\nYou can checkout other commands in `package.json` in the web folder\n\n### Backend\n\n\u003e please see the api folder\n\n- local development without docker:\n  - `pip install pipenv` (If you don't have `pipenv` installed)\n  - `pipenv install`\n  - `pipenv run uvicorn main:app --reload`\n\nBelow commands are already written in `Makefile`, please checkout and change any setting you need first.\n- local development using docker:\n  - `make dev`\n- build a docker image:\n  - `make build`\n- submit a docker image to Google Container Registry:\n  - `make submit`\n- deploy a docker image in Google Container Registry to Google Cloud Run:\n  - `make deploy`\n\n## Todos\n\n- [x] support English\n- [ ] support PWA\n  - [ ] Android\n  - [ ] iOS\n- [ ] export the trained PyTorch models to edge devices for better inference performance\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyyeh%2Fdog-breed-classifier-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyyeh%2Fdog-breed-classifier-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyyeh%2Fdog-breed-classifier-project/lists"}