{"id":16840561,"url":"https://github.com/mitmul/pspnet","last_synced_at":"2025-03-18T04:49:33.272Z","repository":{"id":141385585,"uuid":"99663239","full_name":"mitmul/PSPNet","owner":"mitmul","description":null,"archived":false,"fork":false,"pushed_at":"2017-08-08T07:27:26.000Z","size":8262,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-24T11:44:11.519Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","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/mitmul.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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":"2017-08-08T07:24:16.000Z","updated_at":"2017-08-13T07:27:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"51ef7f47-0a22-44e7-b1a9-1d857b36b337","html_url":"https://github.com/mitmul/PSPNet","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/mitmul%2FPSPNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2FPSPNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2FPSPNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2FPSPNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mitmul","download_url":"https://codeload.github.com/mitmul/PSPNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244159989,"owners_count":20408019,"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":[],"created_at":"2024-10-13T12:37:09.096Z","updated_at":"2025-03-18T04:49:33.253Z","avatar_url":"https://github.com/mitmul.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Pyramid Scene Parsing Network\n\nby Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, details are in [project page](https://hszhao.github.io/projects/pspnet/index.html).\n\n### Introduction\n\nThis repository is for '[Pyramid Scene Parsing Network](https://arxiv.org/abs/1612.01105)', which ranked 1st place in [ImageNet Scene Parsing Challenge 2016](http://image-net.org/challenges/LSVRC/2016/results). The code is modified from Caffe version of [yjxiong](https://github.com/yjxiong/caffe/tree/mem) and [DeepLab v2](https://bitbucket.org/aquariusjay/deeplab-public-ver2) for evaluation. We merge the batch normalization layer named 'bn_layer' in the former one into the later one while keep the original 'batch_norm_layer' in the later one unchanged for compatibility. The difference is that 'bn_layer' contains four parameters as 'slope,bias,mean,variance' while 'batch_norm_layer' contains two parameters as 'mean,variance'. Several evaluation code is borrowed from [MIT Scene Parsing](https://github.com/CSAILVision/sceneparsing).\n\n### Installation\n\nFor installation, please follow the instructions of [Caffe](https://github.com/BVLC/caffe) and [DeepLab v2](https://bitbucket.org/aquariusjay/deeplab-public-ver2). To enable cuDNN for GPU acceleration, cuDNN v4 is needed. If you meet error related with 'matio', please download and install [matio](https://sourceforge.net/projects/matio/files/matio/1.5.2) as required in 'DeepLab v2'.\n\nThe code has been tested successfully on Ubuntu 14.04 and 12.04 with CUDA 7.0.\n\n### Usage\n\n1. Clone the repository:\n\n   ```shell\n   git clone https://github.com/hszhao/PSPNet.git\n   ```\n\n2. Build Caffe and matcaffe:\n\n   ```shell\n   cd $PSPNET_ROOT\n   cp Makefile.config.example Makefile.config\n   vim Makefile.config\n   make -j8 \u0026\u0026 make matcaffe\n   ```\n\n3. Evaluation:\n\n   - Evaluation code is in folder 'evaluation'.\n   - Download trained models and put them in folder 'evaluation/model':\n     - pspnet50\\_ADE20K.caffemodel: [GoogleDrive](https://drive.google.com/open?id=0BzaU285cX7TCN1R3QnUwQ0hoMTA)\n     - pspnet101\\_VOC2012.caffemodel: [GoogleDrive](https://drive.google.com/open?id=0BzaU285cX7TCNVhETE5vVUdMYk0)\n     - pspnet101\\_cityscapes.caffemodel: [GoogleDrive](https://drive.google.com/open?id=0BzaU285cX7TCT1M3TmNfNjlUeEU)\n   - Modify the related paths in 'eval_all.m':\n     - Mainly variables 'data_root' and 'eval_list', and your image list for evaluation should be similarity to that in folder 'evaluation/samplelist' if you use this evaluation code structure. \n     - Matlab 'parfor' evaluation is used and the default GPUs are with ID [0:3]. Modify variable 'gpu_id_array' if needed. We assume that number of images can be divided by number of GPUs; if not, you can just pad your image list or switch to single GPU evaluation by set 'gpu_id_array' be length of one, and change 'parfor' to 'for' loop.\n\n   ```shell\n   cd evaluation\n   vim eval_all.m\n   ```\n\n   - Run the evaluation scripts:\n\n   ```\n   ./run.sh\n   ```\n\n4. Results: \n\n   Prediction results will show in folder 'evaluation/mc_result' and the expected scores are:\n\n   (single scale testing denotes as 'ss' and multiple scale testing denotes as 'ms')\n\n   - PSPNet50 on ADE20K valset (mIoU/pAcc): 41.68/80.04 (ss) and 42.78/80.76 (ms) \n   - PSPNet101 on VOC2012 testset (mIoU): 85.41 (ms)\n   - PSPNet101 on cityscapes valset (mIoU/pAcc): 79.70/96.38 (ss) and 80.91/96.59 (ms)\n\n5. Demo video:\n\n   Video processed by PSPNet101 on cityscapes dataset:\n\n   Merge with colormap on side: [Video1](https://youtu.be/rB1BmBOkKTw)\n\n   Alpha blending with value as 0.5: [Video2](https://youtu.be/HYghTzmbv6Q)\n\n## Citation\n\nIf PSPNet is useful for your research, please consider citing:\n\n    @inproceedings{zhao2017pspnet,\n      author = {Hengshuang Zhao and\n                Jianping Shi and\n                Xiaojuan Qi and\n                Xiaogang Wang and\n                Jiaya Jia},\n      title = {Pyramid Scene Parsing Network},\n      booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n      year = {2017}\n    }\n### Questions\n\nPlease contact 'hszhao@cse.cuhk.edu.hk'\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fpspnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmitmul%2Fpspnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fpspnet/lists"}