{"id":23979350,"url":"https://github.com/filapro/visda2019","last_synced_at":"2025-04-14T03:51:11.058Z","repository":{"id":39740180,"uuid":"200307659","full_name":"filaPro/visda2019","owner":"filaPro","description":"MixMatch Domain Adaptation: Prize-winning solution for both tracks of VisDA 2019 challenge","archived":false,"fork":false,"pushed_at":"2023-03-24T22:34:22.000Z","size":115,"stargazers_count":23,"open_issues_count":1,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-27T17:51:40.475Z","etag":null,"topics":["domain-adaptation","efficient-net","mixmatch","tensorflow","visda"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/filaPro.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}},"created_at":"2019-08-02T23:08:39.000Z","updated_at":"2024-01-04T16:36:20.000Z","dependencies_parsed_at":"2022-08-28T06:40:17.393Z","dependency_job_id":null,"html_url":"https://github.com/filaPro/visda2019","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/filaPro%2Fvisda2019","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filaPro%2Fvisda2019/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filaPro%2Fvisda2019/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filaPro%2Fvisda2019/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/filaPro","download_url":"https://codeload.github.com/filaPro/visda2019/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248819350,"owners_count":21166472,"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":["domain-adaptation","efficient-net","mixmatch","tensorflow","visda"],"created_at":"2025-01-07T09:48:32.918Z","updated_at":"2025-04-14T03:51:11.037Z","avatar_url":"https://github.com/filaPro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"This codebase contains the implementation of our (with [@denemmy](https://github.com/denemmy))\nsolution for [VisDA 2019](http://ai.bu.edu/visda-2019) challenge. \nOur team got **2nd** place on final leaderboard of \n[multi-source](https://competitions.codalab.org/competitions/20256#results) track (with accuracy: .716),\nand **3rd** place of [semi-supervised](https://competitions.codalab.org/competitions/20257#results) (with accuracy: .713).\nThis solution heavily borrows ideas from \nMixMatch ([arxiv](https://arxiv.org/abs/1905.02249), [github](https://github.com/google-research/mixmatch)) \nand EfficientNet ([arxiv](https://arxiv.org/abs/1905.11946), [github](https://github.com/qubvel/efficientnet)). \n\nThe technical report is published on [arxiv](https://arxiv.org/abs/1910.03903).\n\n#### Installation\n\nJust clone this repo, update `PYTHONPATH` and install `requirements.txt` throw `pip`.\nThe code was tested on `ubuntu 16.04` with `python 3.6`, `cuda 10.0`, `cudnn 7.5`.\nYou may also need `wget` and `unzip` packages to download data.\n\n#### Data preparation \n\nDownload and convert images to `.tfrecords`:\n```\npython scripts/download.py\npython scripts/convert_to_tfrecords.py\n```\nThe resulting structure of data directory is shown in [docs/structure.md](docs/structure.md).\n\n#### Training example\n```\npython runners/source_semi_supervised.py\n```\nThe growth of accuracy on sketch domain will be displayed at `stdout` and in log file.\nThe arguments of all scripts are listed in [docs/arguments.md](docs/arguments.md).\n\n#### Achieving leaderboard accuracy\n\nFollow the instructions in [docs/solution.md](docs/solution.md).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilapro%2Fvisda2019","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffilapro%2Fvisda2019","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilapro%2Fvisda2019/lists"}