{"id":13934793,"url":"https://github.com/wohlert/generative-query-network-pytorch","last_synced_at":"2025-07-19T19:31:59.287Z","repository":{"id":48149008,"uuid":"142684409","full_name":"wohlert/generative-query-network-pytorch","owner":"wohlert","description":"Generative Query Network (GQN) in PyTorch as described in \"Neural Scene Representation and Rendering\"","archived":false,"fork":false,"pushed_at":"2019-06-24T08:56:14.000Z","size":45148,"stargazers_count":321,"open_issues_count":1,"forks_count":63,"subscribers_count":14,"default_branch":"master","last_synced_at":"2024-08-08T23:18:53.797Z","etag":null,"topics":["deepmind","generative-models","gqn","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/wohlert.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-07-28T14:36:30.000Z","updated_at":"2024-05-23T06:39:54.000Z","dependencies_parsed_at":"2022-09-19T13:51:31.066Z","dependency_job_id":null,"html_url":"https://github.com/wohlert/generative-query-network-pytorch","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fgenerative-query-network-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fgenerative-query-network-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fgenerative-query-network-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fgenerative-query-network-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wohlert","download_url":"https://codeload.github.com/wohlert/generative-query-network-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226666437,"owners_count":17665030,"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":["deepmind","generative-models","gqn","pytorch"],"created_at":"2024-08-07T23:01:14.355Z","updated_at":"2024-11-27T02:30:48.877Z","avatar_url":"https://github.com/wohlert.png","language":"Jupyter Notebook","readme":"**Update 2019/06/24**: A model trained on 10% of the Shepard-Metzler dataset has been added, the following notebook explains the main features of this model: [nbviewer](https://nbviewer.jupyter.org/github/wohlert/generative-query-network-pytorch/blob/master/mental-rotation.ipynb)\n\n# Generative Query Network\n\nThis is a PyTorch implementation of the Generative Query Network (GQN)\ndescribed in the DeepMind paper \"Neural scene representation and\nrendering\" by Eslami et al. For an introduction to the model and problem\ndescribed in the paper look at the article by [DeepMind](https://deepmind.com/blog/neural-scene-representation-and-rendering/).\n\n![](https://storage.googleapis.com/deepmind-live-cms/documents/gif_2.gif)\n\nThe current implementation generalises to any of the datasets described\nin the paper. However, currently, *only the Shepard-Metzler dataset* has\nbeen implemented. To use this dataset you can use the provided script in\n```\nsh scripts/data.sh data-dir batch-size\n```\n\nThe model can be trained in full by in accordance to the paper by running the\nfile `run-gqn.py` or by using the provided training script\n```\nsh scripts/gpu.sh data-dir\n```\n\n## Implementation\n\nThe implementation shown in this repository consists of all of the\nrepresentation architectures described in the paper along with the\ngenerative model that is similar to the one described in\n\"Towards conceptual compression\" by Gregor et al.\n\nAdditionally, this repository also contains implementations of the **DRAW\nmodel and the ConvolutionalDRAW** model both described by Gregor et al.\n\n","funding_links":[],"categories":["Jupyter Notebook","Paper implementations｜论文实现","LowLevelVision","Paper implementations"],"sub_categories":["Other libraries｜其他库:","3D SemanticSeg","Other libraries:"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwohlert%2Fgenerative-query-network-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwohlert%2Fgenerative-query-network-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwohlert%2Fgenerative-query-network-pytorch/lists"}