{"id":13443634,"url":"https://github.com/Media-Smart/vedacls","last_synced_at":"2025-03-20T17:30:46.641Z","repository":{"id":101954476,"uuid":"266075986","full_name":"Media-Smart/vedacls","owner":"Media-Smart","description":"A classification toolbox based on PyTorch","archived":false,"fork":false,"pushed_at":"2024-02-04T09:04:05.000Z","size":98,"stargazers_count":23,"open_issues_count":1,"forks_count":9,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-10-28T07:39:29.477Z","etag":null,"topics":["classification-toolbox","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Media-Smart.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":"2020-05-22T09:50:20.000Z","updated_at":"2021-09-24T01:50:26.000Z","dependencies_parsed_at":"2024-10-28T05:53:35.955Z","dependency_job_id":null,"html_url":"https://github.com/Media-Smart/vedacls","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/Media-Smart%2Fvedacls","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Media-Smart%2Fvedacls/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Media-Smart%2Fvedacls/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Media-Smart%2Fvedacls/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Media-Smart","download_url":"https://codeload.github.com/Media-Smart/vedacls/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660148,"owners_count":20489296,"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":["classification-toolbox","pytorch"],"created_at":"2024-07-31T03:02:05.826Z","updated_at":"2025-03-20T17:30:44.421Z","avatar_url":"https://github.com/Media-Smart.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"## Introduction\n\nvedacls is an open source classification toolbox based on PyTorch.\n\n## License\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n## Installation\n### Requirements\n\n- Linux\n- Python 3.6+\n- PyTorch 1.4.0 or higher\n- CUDA 9.0 or higher\n\nWe have tested the following versions of OS and softwares:\n\n- OS: Ubuntu 16.04.6 LTS\n- CUDA: 10.2\n- PyTorch 1.4.0\n- Python 3.6.9\n\n### Install vedacls\n\n1. Create a conda virtual environment and activate it.\n\n```shell\nconda create -n vedacls python=3.6.9 -y\nconda activate vedacls\n```\n\n2. Install PyTorch and torchvision following the [official instructions](https://pytorch.org/), *e.g.*,\n\n```shell\nconda install pytorch torchvision -c pytorch\n```\n\n3. Clone the vedacls repository.\n\n```shell\ngit clone https://github.com/Media-Smart/vedacls.git\ncd vedacls\nvedacls_root=${PWD}\n```\n\n4. Install dependencies.\n\n```shell\npip install -r requirements.txt\n```\n\n## Prepare data\nThe catalogue structure of dataset supported by vedacls toolbox is as follows:\n\n```shell\ndata/\n├── train\n│   ├── 0\n│   │   ├── XXX.jpg\n│   │     \n│   ├── 1\n│   ├── 2\n│   ├── ...\n│\n├── val\n│   ├── 0\n│   ├── 1\n│   ├── 2\n│   ├── ...\n│ \n├── test\n    ├── 0\n    ├── 1\n    ├── 2\n    ├── ...\n```\n\n## Train\n\n1. Config\n\nModify some configuration accordingly in the config file like `configs/resnet18.py`\n\n2. Run\n\n```shell\npython tools/train.py configs/resnet18.py\n```\n\nSnapshots and logs will be generated at `${vedacls_root}/workdir/resnet18`\n\n## Test\n\n1. Config\n\nModify some configuration accordingly in the config file like `configs/resnet18.py`\n\n2. Run\n\n```shell\npython tools/test.py configs/resnet18.py checkpoint_path\n```\n\n## Inference\n\n1. Config\n\nModify some configuration accordingly in the config file like `configs/resnet18.py`\n\n2. Run\n\n```shell\npython tools/inference.py configs/resnet18.py checkpoint_path image_path\n```\n\n## Deploy\n1. Install volksdep following the [official instructions](https://github.com/Media-Smart/volksdep)\n\n2. Benchmark(optional)\n```shell\npython tools/deploy/benchmark.py configs/resnet18.py checkpoint_path image_path\n```\nMore available arguments are detailed in [tools/deploy/benchmark.py](https://github.com/Media-Smart/vedacls/blob/master/tools/deploy/benchmark.py)\n\n3. Export model as ONNX or TensorRT engine format\n```shell\npython tools/deploy/export.py configs/resnet18.py checkpoint_path image_path out_model_path\n```\nMore available arguments are detailed in [tools/deploy/export.py](https://github.com/Media-Smart/vedacls/blob/master/tools/deploy/export.py)\n\n4. Inference SDK\n\nYou can refer to [FlexInfer](https://github.com/Media-Smart/flexinfer/blob/master/examples/classifier.py) for details.\n\n## Contact\n\nThis repository is currently maintained by Chenhao Wang ([@C-H-Wong](http://github.com/C-H-Wong)), Hongxiang Cai ([@hxcai](http://github.com/hxcai)), Yichao Xiong ([@mileistone](https://github.com/mileistone)).\n\n## Credits\nWe got a lot of code from [mmcv](https://github.com/open-mmlab/mmcv) and [mmdetection](https://github.com/open-mmlab/mmdetection), thanks to [open-mmlab](https://github.com/open-mmlab).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMedia-Smart%2Fvedacls","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMedia-Smart%2Fvedacls","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMedia-Smart%2Fvedacls/lists"}