{"id":13535559,"url":"https://github.com/shijx12/XNM-Net","last_synced_at":"2025-04-02T01:31:28.545Z","repository":{"id":109368895,"uuid":"151685010","full_name":"shijx12/XNM-Net","owner":"shijx12","description":"Pytorch implementation of \"Explainable and Explicit Visual Reasoning over Scene Graphs \"","archived":false,"fork":false,"pushed_at":"2019-03-17T15:58:22.000Z","size":15140,"stargazers_count":95,"open_issues_count":4,"forks_count":18,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-08-02T08:10:14.935Z","etag":null,"topics":["clevr","cvpr2019","explainable-ai","neural-module-networks","scene-graph","visual-reasoning"],"latest_commit_sha":null,"homepage":"","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/shijx12.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-10-05T07:23:19.000Z","updated_at":"2024-06-26T07:10:01.000Z","dependencies_parsed_at":"2023-07-27T10:15:44.341Z","dependency_job_id":null,"html_url":"https://github.com/shijx12/XNM-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/shijx12%2FXNM-Net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shijx12%2FXNM-Net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shijx12%2FXNM-Net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shijx12%2FXNM-Net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shijx12","download_url":"https://codeload.github.com/shijx12/XNM-Net/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222788514,"owners_count":17037777,"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":["clevr","cvpr2019","explainable-ai","neural-module-networks","scene-graph","visual-reasoning"],"created_at":"2024-08-01T08:00:58.395Z","updated_at":"2024-11-02T23:31:39.361Z","avatar_url":"https://github.com/shijx12.png","language":"Python","funding_links":[],"categories":["Image VQA","Scene Graph Generation:"],"sub_categories":["2019"],"readme":"# eXplainable and eXplicit Neural Modules (XNMs)\n\nPytorch implementation of paper \n\n**[Explainable and Explicit Visual Reasoning over Scene Graphs](https://arxiv.org/abs/1812.01855)**\n\u003cbr\u003e\n[Jiaxin Shi](https://shijx12.github.io), [Hanwang Zhang](http://www.ntu.edu.sg/home/hanwangzhang/#aboutme), Juanzi Li\n\nFlowchart of our model:\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"images/flowchart.png\" width=\"60%\"\u003e\n\u003c/div\u003e\u003cbr/\u003e\n\nA visualization of our reasoning process:\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"images/example.png\"\u003e\n\u003c/div\u003e\u003cbr/\u003e\n\nIf you find this code useful in your research, please cite\n``` tex\n@inproceedings{shi2019explainable,\n  title={Explainable and Explicit Visual Reasoning over Scene Graphs},\n  author={Jiaxin Shi, Hanwang Zhang, Juanzi Li},\n  booktitle={CVPR},\n  year={2019}\n}\n```\n\n\n\n## Requirements\n- python==3.6\n- pytorch==0.4.0\n- h5py \n- tqdm\n- matplotlib\n\n\n## Experiments\nWe have 4 experiment settings:\n- CLEVR dataset, Det setting (i.e., using detected scene graphs). Codes are in the directory `./exp_clevr_detected`.\n- CLEVR dataset, GT setting (i.e., using ground truth scene graphs), attention is computed by softmax function over the label space. Codes are in `./exp_clevr_gt_softmax`.\n- CLEVR dataset, GT setting, attention is computed by sigmoid function. Codes are in `./exp_clevr_gt_sigmoid`.\n- VQA2.0 dataset, detected scene graphs. Codes are in `./exp_vqa`.\n\nWe have a **separate README for each experiment setting** as an instruction to reimplement our reported results.\nFeel free to contact me if you have any problems: shijx12@gmail.com\n\n## Acknowledgement\n- We refer to the repo [clevr-iep](https://github.com/facebookresearch/clevr-iep) for preprocessing codes.\n- Our implementations of module model and dataloader are based on [tbd-net](https://github.com/davidmascharka/tbd-nets).\n- Our stacked neural module implementation in `./exp_vqa` is based on Hu's [StackNMN](https://github.com/ronghanghu/snmn).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshijx12%2FXNM-Net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshijx12%2FXNM-Net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshijx12%2FXNM-Net/lists"}