{"id":16271598,"url":"https://github.com/tonysy/drn-mxnet","last_synced_at":"2025-10-04T04:32:06.105Z","repository":{"id":96964870,"uuid":"144732045","full_name":"tonysy/DRN-MXNet","owner":"tonysy","description":"Dense Relation Network: Learning Consistent and Context-Aware Representation For Semantic Image Segmentation. Modification of DRN source code","archived":false,"fork":false,"pushed_at":"2018-08-16T03:16:25.000Z","size":328,"stargazers_count":25,"open_issues_count":4,"forks_count":4,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-01-06T03:00:32.902Z","etag":null,"topics":["artificial-intelligence","computer-vision","deep-learning","semantic-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","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/tonysy.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-08-14T14:32:40.000Z","updated_at":"2024-01-04T16:25:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"48eff4f0-7dcb-4875-80b1-c86ec2988750","html_url":"https://github.com/tonysy/DRN-MXNet","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/tonysy%2FDRN-MXNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonysy%2FDRN-MXNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonysy%2FDRN-MXNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonysy%2FDRN-MXNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tonysy","download_url":"https://codeload.github.com/tonysy/DRN-MXNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235217925,"owners_count":18954520,"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":["artificial-intelligence","computer-vision","deep-learning","semantic-segmentation"],"created_at":"2024-10-10T18:14:07.750Z","updated_at":"2025-10-04T04:32:00.628Z","avatar_url":"https://github.com/tonysy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DRN-MXNet\nThe [author](https://github.com/zhuangyqin/DRN.git) of this projcet doesn't release the config file and usages.\nI was working on semantic segmentation based on MXNet. So I have fix the errors and add usage for the original project.\n\n## 1. Setup\n- Python2.7\n- OpenCV\n- CUDA 8 or 9\n\n### Build MXNet from Source:\n- Clone the mxnet source code\n- Put `ordering_op-inl.h` into `incubator-mxnet/src/operator/tensor`\n- Put `softmax**` into `incubator-mxnet/src/operator/contrib`\n- Follow the official instructions to build and install\n- `sh init.sh` to build some libs for dataloader and detection task\n\n### Get data and model\n- Put data into `data/cistycapes`, you can use soft link to add the dataset\n    `ln -s \u003cdataset\u003e ./data/cityscapes`\n- Use the model provided by autho to load params(Optional)\n    - [Model](https://pan.baidu.com/s/14_zNi_m7hjv-sMWjY0D1Hw)\n    - It's not the pretrained model, so I just use it for test.\n    - I will try to generate a pretrained model recently\n\n### Train with a simple config file\nBecause the original paper is not public now, I can only use some magic number of option to run this code. I am working on understanding the model from the code.\n#### Train\n`python2 experiment/deeplab/drn_train.py --cfg experiment/deeplab/cfgs/resnet_v2_38_deeplab_dcn_gru_v7.yaml`\n#### Test\nTBD\n\n### Others \n\u003e main result on ade20k testing is 0.5635(symbol-v11)-single model main result on cityscapes testing is 82.4(symbol-v7) and 82.8(symbol-v13) - single model\n\u003e If you have question or some advice, email me 'zhuangyq@pku.edu.cn'\n\u003e The model release on 'https://pan.baidu.com/s/14_zNi_m7hjv-sMWjY0D1Hw'\n\nThanks the author anyway!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftonysy%2Fdrn-mxnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftonysy%2Fdrn-mxnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftonysy%2Fdrn-mxnet/lists"}