{"id":18614557,"url":"https://github.com/minar09/asu-net","last_synced_at":"2025-04-11T00:30:50.296Z","repository":{"id":67769840,"uuid":"186258446","full_name":"minar09/ASU-Net","owner":"minar09","description":"ASU-Net: Attention to Scale with U-Net for Semantic Segmentation (Implemented with TensorFlow)","archived":false,"fork":false,"pushed_at":"2019-05-15T06:31:24.000Z","size":51,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-25T06:51:12.555Z","etag":null,"topics":["asu-net","attention","attention-to-scale","clothing-parsing","fashion-parsing","segmentation","semantic-segmentation","tensorflow","u-net"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/minar09.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":"2019-05-12T13:27:43.000Z","updated_at":"2022-05-29T14:10:08.000Z","dependencies_parsed_at":"2023-12-03T07:15:11.341Z","dependency_job_id":null,"html_url":"https://github.com/minar09/ASU-Net","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/minar09%2FASU-Net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FASU-Net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FASU-Net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FASU-Net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/minar09","download_url":"https://codeload.github.com/minar09/ASU-Net/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248322227,"owners_count":21084333,"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":["asu-net","attention","attention-to-scale","clothing-parsing","fashion-parsing","segmentation","semantic-segmentation","tensorflow","u-net"],"created_at":"2024-11-07T03:26:02.234Z","updated_at":"2025-04-11T00:30:50.285Z","avatar_url":"https://github.com/minar09.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ASU-Net: Attention to Scale with U-Net for Semantic Segmentation\nThis is a TensorFlow implementation of our ASU-Net. We train Multi-scale U-Net model first, and then the ASU-Net.\nFor more details, check our paper. (Link coming soon)\n\n1. [Prerequisites](#prerequisites)\n2. [Dataset](#dataset)\n3. [Training](#training)\n4. [Testing](#testing)\n5. [Visualizing](#visualizing)\n6. [CRF](#crf)\n7. [BFSCORE](#bfscore)\n\n## Directory Structure\n\n```bash\n└── __init__.py\n└── .gitignore\n└── ASUNet.py\n└── BatchDatasetReader.py\n└── bfscore.py\n└── CalculateUtil.py\n└── denseCRF.py\n└── EvalMetrics.py\n└── function_definitions.py\n└── LICENSE\n└── read_10k_data.py\n└── read_CFPD_data.py\n└── read_LIP_data.py\n└── README.md\n└── requirements.txt\n└── TensorflowUtils.py\n└── test_human.py\n└── UNetMSc.py\n\n```\n\n## Prerequisites\n - For required packages installation, run `pip install -r requirements.txt`\n - pydensecrf installation in windows with conda: `conda install -c conda-forge pydensecrf`. For linux, use pip: `pip install pydensecrf`.\n - Check dataset directory in `read_dataset` function of corresponding data reading script, for example, for LIP dataset, check paths in `read_LIP_data.py` and modify as necessary.\n\n## Dataset\n - Right now, there are dataset supports for 3 datasets. Set your directory path in the corresponding dataset reader script.\n - [CFPD](https://github.com/hrsma2i/dataset-CFPD) (For preparing CFPD dataset, you can visit here: https://github.com/minar09/dataset-CFPD-windows)\n - [LIP](http://www.sysu-hcp.net/lip/)\n - 10k (Fashion)\n - If you want to use your own dataset, please create your dataset reader. (Check `read_CFPD_data.py` for example, on how to put directory and stuff)\n\n## Training\n - To train model simply execute `python UNetMSc.py` and then `python ASUNet.py`\n - You can add training flag as well, for example: `python UNetMSc.py --mode=train` and `python ASUNet.py --mode=train`\n - `debug` flag can be set during training to add information regarding activations, gradients, variables etc.\n - Set your hyper-parameters in the corresponding model script\n\n## Testing\n - To test and evaluate results use flag `--mode=test`, e.g., `python ASUNet.py --mode=test`\n - After testing and evaluation is complete, final results will be printed in the console, and the corresponding files will be saved in the \"logs\" directory.\n - Set your hyper-parameters in the corresponding model script\n\n## Visualizing\n - To visualize results for a random batch of images use flag `--mode=visualize`\n - Set your hyper-parameters in the corresponding model script\n\n## CRF\n - Running testing will apply CRF by default.\n - If you want to run standalone, run `python denseCRF.py`, after setting your paths.\n\n## BFSCORE\n - Run `python bfscore.py`, after setting your paths.\n - For more details, visit https://github.com/minar09/bfscore_python\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Fasu-net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fminar09%2Fasu-net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Fasu-net/lists"}