{"id":19899146,"url":"https://github.com/tootouch/vit_repo","last_synced_at":"2025-08-23T19:14:44.068Z","repository":{"id":45788670,"uuid":"386965237","full_name":"TooTouch/ViT_repo","owner":"TooTouch","description":" Pytorch version of the pre-trained VIT models released by google research ","archived":false,"fork":false,"pushed_at":"2021-07-17T15:22:40.000Z","size":30,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-01T06:43:26.497Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/TooTouch.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}},"created_at":"2021-07-17T14:51:41.000Z","updated_at":"2023-07-01T00:01:05.000Z","dependencies_parsed_at":"2022-07-17T00:46:04.187Z","dependency_job_id":null,"html_url":"https://github.com/TooTouch/ViT_repo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TooTouch/ViT_repo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2FViT_repo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2FViT_repo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2FViT_repo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2FViT_repo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TooTouch","download_url":"https://codeload.github.com/TooTouch/ViT_repo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2FViT_repo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271765024,"owners_count":24817286,"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":"2025-08-23T02:00:09.327Z","response_time":69,"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":[],"created_at":"2024-11-12T20:07:19.597Z","updated_at":"2025-08-23T19:14:44.008Z","avatar_url":"https://github.com/TooTouch.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ViT_repo\nPytorch version of the pre-trained VIT models released by google research \n\n# Environments\n\n```\nml-collections\neinops=0.3.0\ntorch=1.7.0\ntorchvision=0.8.0\n```\n# Load a Pretrained Model\n\n**Available Pretrained Models**\n\nI will update other models ASAP.\n\nPretrained models in [here](https://console.cloud.google.com/storage/browser/vit_models/imagenet21k?pageState=(%22StorageObjectListTable%22:(%22f%22:%22%255B%255D%22))\u0026prefix=\u0026forceOnObjectsSortingFiltering=false). Model settings and performances in [here](https://github.com/google-research/vision_transformer#available-vit-models)\n\n- ViT-B_16\n- ViT-B_32\n- ViT-L_16\n- ViT-L_32\n- ViT-H_14\n- R50-ViT-B_16\n- R50-ViT-L_16\n\nThis code is in [notebook](https://github.com/TooTouch/ViT_repo/blob/main/convert.ipynb).\n\n```python\nfrom ViT.model import VisionTransformer, CONFIGS\n\nclass Config:\n    img_size         = 224\n    vit_patches_size = 16\n    vit_name         = 'ViT-L_16'\nargs = Config()\n\n# model config\nconfig_vit = CONFIGS[args.vit_name]\nprint('pretrained path: ',config_vit.pretrained_path)\n\nif args.vit_name.find('R50') != -1:\n    config_vit.patches.grid = (int(args.img_size / args.vit_patches_size), int(args.img_size / args.vit_patches_size))\n\n# build model\nmodel = VisionTransformer(config_vit, vis=True)\nmodel.load_from(config_vit)\n```\n\n# Code Reference\n\n- https://github.com/Beckschen/TransUNet/tree/d68a53a2da73ecb496bb7585340eb660ecda1d59","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftootouch%2Fvit_repo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftootouch%2Fvit_repo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftootouch%2Fvit_repo/lists"}