{"id":15707500,"url":"https://github.com/robmarkcole/pytorch-serve-from-colab","last_synced_at":"2026-05-10T09:33:20.653Z","repository":{"id":85844513,"uuid":"203994584","full_name":"robmarkcole/pytorch-serve-from-colab","owner":"robmarkcole","description":"Serve up pytorch models running on the free GPU of Colab","archived":false,"fork":false,"pushed_at":"2023-05-01T20:11:55.000Z","size":60,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-25T00:07:47.236Z","etag":null,"topics":["colab-notebook","colaboratory","flask","pytorch"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/robmarkcole.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-08-23T12:30:44.000Z","updated_at":"2023-12-01T02:58:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"1f1b6075-cb88-40b5-a9ad-fd00e2a3d45c","html_url":"https://github.com/robmarkcole/pytorch-serve-from-colab","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2Fpytorch-serve-from-colab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2Fpytorch-serve-from-colab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2Fpytorch-serve-from-colab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2Fpytorch-serve-from-colab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/robmarkcole","download_url":"https://codeload.github.com/robmarkcole/pytorch-serve-from-colab/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246342994,"owners_count":20761947,"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","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":["colab-notebook","colaboratory","flask","pytorch"],"created_at":"2024-10-03T20:40:40.168Z","updated_at":"2026-05-10T09:33:20.612Z","avatar_url":"https://github.com/robmarkcole.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## pytorch-serve-from-colab\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/robmarkcole/pytorch-serve-from-colab/blob/master/pytorch-serve-colab.ipynb)\n\n* Serve up a pytorch model via flask and access on a publix URL [via ngrok](https://github.com/gstaff/flask-ngrok)\n* Use as a research tool for batch processing or just as an on demand services, all GPU accelerated :) Be sure to read the [Colab FAQ](https://research.google.com/colaboratory/faq.html)\n\n## Run on colab\nOpen the notebook on [colab](https://colab.research.google.com) by clicking on the `Open In Colab` button above and follow the instructions to mount your Google drive. Then you can make a request from anywhere on the internet (substituting the ngrok url below for your own) e.g:\n```\ncurl -X POST -F file=@hummingbird.jpg http://6801b5e1.ngrok.io/predict\n```\n\n## Run app locally\nRun the flask app, this requires sudo on my machine:\n```\nsudo python3 app.py \n```\nCheck that the app is accessible on the ngrok url. Then make a prediction:\n```\ncurl -X POST -F file=@hummingbird.jpg http://localhost:5000/predict\n\n{\n  \"class_id\": \"n01833805\", \n  \"class_name\": \"hummingbird\"\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fpytorch-serve-from-colab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frobmarkcole%2Fpytorch-serve-from-colab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fpytorch-serve-from-colab/lists"}