{"data":{"slug":"tristandeleu-pytorch-meta","name":"pytorch-meta","tagline":"Extensions and data-loaders for few-shot learning & meta-learning in PyTorch","github_url":"https://github.com/tristandeleu/pytorch-meta","owner":"tristandeleu","repo":"pytorch-meta","owner_avatar_url":"https://avatars.githubusercontent.com/u/2018752?v=4","primary_language":"Python","stars":2062,"forks":264,"topics":["few-shot-learning","meta-learning","pytorch"],"archived":false,"github_pushed_at":"2023-07-17T16:05:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tristandeleu-pytorch-meta","markdown_url":"https://www.graphcanon.com/tools/tristandeleu-pytorch-meta.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tristandeleu-pytorch-meta","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tristandeleu-pytorch-meta","description":"A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch","homepage_url":"https://tristandeleu.github.io/pytorch-meta/","license":"MIT","open_issues":61,"watchers":40,"ai_summary":"Provides modules that facilitate the development of few-shot learning and meta-learning models using PyTorch framework.","readme_excerpt":"## Installation\nYou can install Torchmeta either using Python's package manager pip, or from source. To avoid any conflict with your existing Python setup, it is suggested to work in a virtual environment with [`virtualenv`](https://docs.python-guide.org/dev/virtualenvs/). To install `virtualenv`:\n```bash\npip install --upgrade virtualenv\nvirtualenv venv\nsource venv/bin/activate\n```\n\n#### Requirements\n - Python 3.6 or above\n - PyTorch 1.4 or above\n - Torchvision 0.5 or above\n\n#### Using pip\nThis is the recommended way to install Torchmeta:\n```bash\npip install torchmeta\n```\n\n#### From source\nYou can also install Torchmeta from source. This is recommended if you want to contribute to Torchmeta.\n```bash\ngit clone https://github.com/tristandeleu/pytorch-meta.git\ncd pytorch-meta\npython setup.py install\n```","github_created_at":"2018-12-04T23:36:45+00:00","created_at":"2026-07-11T23:36:49.378721+00:00","updated_at":"2026-08-04T12:00:59.218996+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"data-loaders","name":"data-loaders"},{"slug":"extensions","name":"extensions"},{"slug":"few-shot-learning","name":"few-shot-learning"},{"slug":"meta-learning","name":"meta-learning"},{"slug":"pytorch","name":"pytorch"}],"trust":{"provenance":{"is_fork":false,"github_id":160432571,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-04T12:00:57.817Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1113,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:36:53.677Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-04T12:00:58.725Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-04T12:00:58.725Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-04T12:00:58.725Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When developing models that require handling few-shot learning scenarios where only a small amount of labeled data is available.","For researchers or developers interested in leveraging pre-built modules and data-loaders to accelerate the prototyping phase in meta-learning projects."],"when_not_to_use":["If your project requires extensive support for traditional deep learning tasks, as PyTorch-Meta does not offer comprehensive utilities beyond few-shot learning and meta-learning.","For those strictly adhering to a single ecosystem that does not include the PyTorch framework or its specific versions below 1.4."],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:13:03.493Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"PyTorch-Meta focuses on facilitating few-shot learning and meta-learning with PyTorch, offering extensions and data-loaders specifically for these tasks."}]}}