{"id":17319854,"url":"https://github.com/saransh-cpp/scenenet-backend","last_synced_at":"2026-04-14T06:33:32.022Z","repository":{"id":105022396,"uuid":"435009164","full_name":"Saransh-cpp/SceneNet-Backend","owner":"Saransh-cpp","description":"Scenery detection using transfer learning. (Backend)","archived":false,"fork":false,"pushed_at":"2021-12-20T15:33:41.000Z","size":102914,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T02:44:26.851Z","etag":null,"topics":["api-rest","fastapi","heroku","python3","transfer-learning","vgg19"],"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/Saransh-cpp.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}},"created_at":"2021-12-04T21:06:37.000Z","updated_at":"2021-12-29T22:41:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"cff1d9a2-489c-4eb9-964a-d4dad6019a16","html_url":"https://github.com/Saransh-cpp/SceneNet-Backend","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Saransh-cpp/SceneNet-Backend","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Saransh-cpp%2FSceneNet-Backend","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Saransh-cpp%2FSceneNet-Backend/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Saransh-cpp%2FSceneNet-Backend/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Saransh-cpp%2FSceneNet-Backend/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Saransh-cpp","download_url":"https://codeload.github.com/Saransh-cpp/SceneNet-Backend/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Saransh-cpp%2FSceneNet-Backend/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273702474,"owners_count":25152902,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":["api-rest","fastapi","heroku","python3","transfer-learning","vgg19"],"created_at":"2024-10-15T13:27:44.076Z","updated_at":"2026-04-14T06:33:31.985Z","avatar_url":"https://github.com/Saransh-cpp.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## SceneNet Backend\n\nScenery detection using transfer learning.\n\n## Description\nThe API uses the `VGG19` convoution neural network, which is trained on a dataset of 10903 images belonging to 67 different classes.\nThe classes (as used in the code) -\n```py\nlabels = {\n    0: \"airport_inside\",\n    1: \"artstudio\",\n    2: \"auditorium\",\n    3: \"bakery\",\n    4: \"bar\",\n    5: \"bathroom\",\n    6: \"bedroom\",\n    7: \"bookstore\",\n    8: \"bowling\",\n    9: \"buffet\",\n    10: \"casino\",\n    11: \"children_room\",\n    12: \"church_inside\",\n    13: \"classroom\",\n    14: \"cloister\",\n    15: \"closet\",\n    16: \"clothingstore\",\n    17: \"computerroom\",\n    18: \"concert_hall\",\n    19: \"corridor\",\n    20: \"deli\",\n    21: \"dentaloffice\",\n    22: \"dining_room\",\n    23: \"elevator\",\n    24: \"fastfood_restaurant\",\n    25: \"florist\",\n    26: \"gameroom\",\n    27: \"garage\",\n    28: \"greenhouse\",\n    29: \"grocerystore\",\n    30: \"gym\",\n    31: \"hairsalon\",\n    32: \"hospitalroom\",\n    33: \"inside_bus\",\n    34: \"inside_subway\",\n    35: \"jewelleryshop\",\n    36: \"kindergarden\",\n    37: \"kitchen\",\n    38: \"laboratorywet\",\n    39: \"laundromat\",\n    40: \"library\",\n    41: \"livingroom\",\n    42: \"lobby\",\n    43: \"locker_room\",\n    44: \"mall\",\n    45: \"meeting_room\",\n    46: \"movietheater\",\n    47: \"museum\",\n    48: \"nursery\",\n    49: \"office\",\n    50: \"operating_room\",\n    51: \"pantry\",\n    52: \"poolinside\",\n    53: \"prisoncell\",\n    54: \"restaurant\",\n    55: \"restaurant_kitchen\",\n    56: \"shoeshop\",\n    57: \"stairscase\",\n    58: \"studiomusic\",\n    59: \"subway\",\n    60: \"toystore\",\n    61: \"trainstation\",\n    62: \"tv_studio\",\n    63: \"videostore\",\n    64: \"waitingroom\",\n    65: \"warehouse\",\n    66: \"winecellar\",\n}\n```\n\n## Usage\n- The API can be accessed through the URL - https://scene-net.herokuapp.com/\n- To predict an image's class, use the `/predict` endpoint\n- For the complete documentation refer to - https://scene-net.herokuapp.com/docs\n\n## Running locally\n### To train the model locally -\n1. Fork and clone the repository\n```\ngit clone https://github.com/\u003cyour_username\u003e/SceneNet-Backend\n```\n2. Create a new virtual environment\n```\npython -m venve .venv\n```\n3. Activate the virtual environment\n```\n.venv/Scripts/activate\n```\n4. Install requirements for training\n```\npython -m pip install -r train_model/train_requirements.txt\n```\n5. Run the jupyter in the virtual environment\n```\nipython kernel install --user --name=venv\n# select the kernel named after your virtual environment in jupyter notebook\n```\n### To run the API locally-\n1. Fork and clone the repository\n```\ngit clone https://github.com/\u003cyour_username\u003e/SceneNet-Backend\n```\n2. Create a new virtual environment\n```\npython -m venv .venv\n```\n3. Activate the virtual environment\n```\n.venv/Scripts/activate\n```\n4. Install requirements for training (the `Heroku` deployment uses `tensorflow-cpu` and `opencv-python-headless` because of the memory limitations, but you can switch to `tensorflow` and `opencv-python` if you are running this locally)\n```\npython -m pip install -r requirements.txt\n```\n5. Fire up the API\n```\nuvicorn backend.backend:app --reload\n```\n\n## Dataset used\n\nhttps://www.kaggle.com/itsahmad/indoor-scenes-cvpr-2019\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaransh-cpp%2Fscenenet-backend","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaransh-cpp%2Fscenenet-backend","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaransh-cpp%2Fscenenet-backend/lists"}