{"id":13493057,"url":"https://github.com/jhhuang96/ConvLSTM-PyTorch","last_synced_at":"2025-03-28T11:31:35.327Z","repository":{"id":38277020,"uuid":"202096131","full_name":"jhhuang96/ConvLSTM-PyTorch","owner":"jhhuang96","description":"ConvLSTM/ConvGRU (Encoder-Decoder) with PyTorch on Moving-MNIST","archived":false,"fork":false,"pushed_at":"2022-10-13T02:04:37.000Z","size":9786,"stargazers_count":386,"open_issues_count":9,"forks_count":85,"subscribers_count":9,"default_branch":"master","last_synced_at":"2024-10-31T07:34:12.475Z","etag":null,"topics":["convgru","convlstm","encoder-decoder","gru","lstm","pytorch-implementation","rnn","spatio-temporal","time-series"],"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/jhhuang96.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}},"created_at":"2019-08-13T08:10:37.000Z","updated_at":"2024-10-27T03:09:31.000Z","dependencies_parsed_at":"2022-07-12T17:22:39.088Z","dependency_job_id":null,"html_url":"https://github.com/jhhuang96/ConvLSTM-PyTorch","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/jhhuang96%2FConvLSTM-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhhuang96%2FConvLSTM-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhhuang96%2FConvLSTM-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhhuang96%2FConvLSTM-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jhhuang96","download_url":"https://codeload.github.com/jhhuang96/ConvLSTM-PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246020949,"owners_count":20710855,"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":["convgru","convlstm","encoder-decoder","gru","lstm","pytorch-implementation","rnn","spatio-temporal","time-series"],"created_at":"2024-07-31T19:01:11.840Z","updated_at":"2025-03-28T11:31:34.520Z","avatar_url":"https://github.com/jhhuang96.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":["Networks"],"readme":"\r\n\r\n# ConvLSTM-Pytorch\r\n\r\n## ConvRNN cell\r\n\r\nImplement ConvLSTM/ConvGRU cell with Pytorch. This idea has been proposed in this paper: [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://arxiv.org/abs/1506.04214)\r\n\r\n## Experiments with ConvLSTM on MovingMNIST\r\n\r\nEncoder-decoder structure. Takes in a sequence of 10 movingMNIST fames and attempts to output the remaining frames.\r\n\r\n## Instructions\r\n\r\nRequires `Pytorch v1.1` or later (and GPUs)\r\n\r\nClone repository\r\n\r\n```\r\ngit clone https://github.com/jhhuang96/ConvLSTM-PyTorch.git\r\n```\r\n\r\nTo run endoder-decoder network for prediction moving-mnist:\r\n\r\n```python\r\npython main.py\r\n```\r\n\r\n## Moving Mnist Generator\r\n\r\nThe script ``data/mm.py`` is the script to generate customized Moving Mnist based on [MNIST](http://yann.lecun.com/exdb/mnist/). \r\n\r\n```python\r\nMovingMNIST(is_train=True,\r\n            root='data/',\r\n            n_frames_input=args.frames_input,\r\n            n_frames_output=args.frames_output,\r\n            num_objects=[3])\r\n```\r\n\r\n- is_train: If True, use script to generate data. If False, directly use Moving Mnist data  downloaded from http://www.cs.toronto.edu/~nitish/unsupervised_video/\r\n- root: The path of MNIST data\r\n- n_frames_input: Number of input frames (int)\r\n- n_frames_output: Number of output frames (int)\r\n- num_objects:  Number of digits in a frame (List) . [3] means there are 3 digits in each frame\r\n\r\n## Result\r\n\r\n ![Result](https://github.com/jhhuang96/ConvLSTM-PyTorch/tree/master/images/movingmnist.png)\r\n\r\n- The first line is the real data for the first 10 frames\r\n- The second line is prediction of the model for the last 10 frames\r\n\r\n## Citation\r\n\r\n```\r\n@inproceedings{xingjian2015convolutional,\r\n  title={Convolutional LSTM network: A machine learning approach for precipitation nowcasting},\r\n  author={Xingjian, SHI and Chen, Zhourong and Wang, Hao and Yeung, Dit-Yan and Wong, Wai-Kin and Woo, Wang-chun},\r\n  booktitle={Advances in neural information processing systems},\r\n  pages={802--810},\r\n  year={2015}\r\n}\r\n@inproceedings{xingjian2017deep,\r\n    title={Deep learning for precipitation nowcasting: a benchmark and a new model},\r\n    author={Shi, Xingjian and Gao, Zhihan and Lausen, Leonard and Wang, Hao and Yeung, Dit-Yan and Wong, Wai-kin and Woo, Wang-chun},\r\n    booktitle={Advances in Neural Information Processing Systems},\r\n    year={2017}\r\n}\r\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjhhuang96%2FConvLSTM-PyTorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjhhuang96%2FConvLSTM-PyTorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjhhuang96%2FConvLSTM-PyTorch/lists"}