{"id":20990641,"url":"https://github.com/wnjxyk/step","last_synced_at":"2025-09-02T17:43:17.483Z","repository":{"id":154800620,"uuid":"414112003","full_name":"WNJXYK/Step","owner":"WNJXYK","description":"This is an pytorch implementation of STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data","archived":false,"fork":false,"pushed_at":"2022-03-19T08:17:07.000Z","size":33,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-02T22:22:36.168Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/WNJXYK.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":"2021-10-06T07:27:36.000Z","updated_at":"2024-02-07T06:59:31.000Z","dependencies_parsed_at":"2023-05-07T12:31:27.116Z","dependency_job_id":null,"html_url":"https://github.com/WNJXYK/Step","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/WNJXYK%2FStep","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WNJXYK%2FStep/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WNJXYK%2FStep/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WNJXYK%2FStep/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WNJXYK","download_url":"https://codeload.github.com/WNJXYK/Step/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254222268,"owners_count":22034854,"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":[],"created_at":"2024-11-19T06:34:49.232Z","updated_at":"2025-05-14T20:31:49.690Z","avatar_url":"https://github.com/WNJXYK.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Step\n\nThis is an pytorch implementation of `STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data`\n\n## Requirements\n\nInstall conda environment via `environment.yaml`.\n\n## Out-of-distribution Dataset\n\nDownload out-of-distributin datasets provided by ODIN: [Google Drive](https://drive.google.com/drive/folders/1aPyNXDib0uUb9a0CUK1DhelqM5_TLX7u?usp=sharing)\n\nFor example, you can download `Imagenet.tar.gz` into `./data/` directory and run script `tar -xvzf Imagenet.tar.gz`.\n\n## Pre-trained Model\n\nFor a quick start, you can download our pre-trained model to `./files/` directory. \n\nDownload Link: [Google Drive](https://drive.google.com/drive/folders/1PaV6rn168sYDKZ8opI_F1Qkmw2AHyIEp?usp=sharing)\n\n\nYou can also run the following scripts to train your own pre-trained model.\n```bash\npython SimCLR.py --out-dataset=LSUN --in-dataset=Cifar10\n```\n\n## Usage\n\n\nChoose the datasets you want and run the script: `python Step.py --out-dataset={LSUN, LSUN_resize, Imagenet, Imagenet_resize} --in-dataset={Cifar10, Cifar100}`. For example, you can run the following script: \n```\npython Step.py --out-dataset=LSUN --in-dataset=Cifar10\n```\n\nWhen the training stage is over, the final model will be stored in `./files/`, and the result will be printed and stored in `./results/`.\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwnjxyk%2Fstep","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwnjxyk%2Fstep","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwnjxyk%2Fstep/lists"}