{"id":13678119,"url":"https://github.com/S-aiueo32/lpips-pytorch","last_synced_at":"2025-04-29T12:33:33.251Z","repository":{"id":37222183,"uuid":"237387528","full_name":"S-aiueo32/lpips-pytorch","owner":"S-aiueo32","description":"A simple and useful implementation of LPIPS.","archived":false,"fork":false,"pushed_at":"2023-09-29T16:38:00.000Z","size":679,"stargazers_count":151,"open_issues_count":8,"forks_count":25,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-08-02T13:20:49.315Z","etag":null,"topics":["deep-learning","deep-neural-networks","lpips","perceptual-metric","perceptual-similarity"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/S-aiueo32.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}},"created_at":"2020-01-31T08:16:55.000Z","updated_at":"2024-06-14T17:29:20.000Z","dependencies_parsed_at":"2024-01-14T15:21:40.592Z","dependency_job_id":"a7d1afad-9fa0-4785-bee1-04118cb46d14","html_url":"https://github.com/S-aiueo32/lpips-pytorch","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/S-aiueo32%2Flpips-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S-aiueo32%2Flpips-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S-aiueo32%2Flpips-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S-aiueo32%2Flpips-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/S-aiueo32","download_url":"https://codeload.github.com/S-aiueo32/lpips-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224173545,"owners_count":17268128,"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":["deep-learning","deep-neural-networks","lpips","perceptual-metric","perceptual-similarity"],"created_at":"2024-08-02T13:00:50.289Z","updated_at":"2024-11-11T20:31:00.628Z","avatar_url":"https://github.com/S-aiueo32.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# lpips-pytorch\n[![CircleCI](https://circleci.com/gh/S-aiueo32/lpips-pytorch.svg?style=svg)](https://circleci.com/gh/S-aiueo32/lpips-pytorch)  ![](https://img.shields.io/badge/LPIPS%20ver.-0.1-brightgreen)\n\n## Description\nDeveloping perceptual distance metrics is a major topic in recent image processing problems.\nLPIPS[1] is a state-of-the-art perceptual metric based on human similarity judgments.\nThe official implementation is not only publicly available as a metric, but also enables users to train the new metric by themselves.\nIn other words, The official implementation has less simplicity by the high-level wrapping for training.\nThis repository provides an alternative simple and useful implementation of LPIPS.\nThis output is definitely the same result because the weights are converted from the original one.\n\n## Requirement\n- `torch` \u003e= 1.3\n- `torchvision` \u003e= 0.4\n\n## Usage\n```python\nfrom lpips_pytorch import LPIPS, lpips\n\n\n# define as a criterion module (recommended)\ncriterion = LPIPS(\n    net_type='alex',  # choose a network type from ['alex', 'squeeze', 'vgg']\n    version='0.1'  # Currently, v0.1 is supported\n)\nloss = criterion(x, y)\n\n# functional call\nloss = lpips(x, y, net_type='alex', version='0.1')\n```\n\n## Install\n1. Clone this repository and move into your project\n    ```shell\n    ~ $ git clone https://github.com/S-aiueo32/lpips-pytorch.git\n    ~ $ mv lpips-pytorch/lpips-pytorch \u003cYOUR_PROJECT\u003e\n    ```\n2. Install by `pip`\n    ```shell\n    $ pip install git+https://github.com/S-aiueo32/lpips-pytorch.git\n    ```\n\n## License\n[BSD 2-Clause \"Simplified\" License](LICENSE).\n\n## Reference\n1. Zhang, Richard, et al. \"The unreasonable effectiveness of deep features as a perceptual metric.\" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.\n\n## Acknowledgements\nThis project directly uses the original weights, many thanks to the authors.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FS-aiueo32%2Flpips-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FS-aiueo32%2Flpips-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FS-aiueo32%2Flpips-pytorch/lists"}