{"id":17985592,"url":"https://github.com/yuantinghsieh/tf_tcn","last_synced_at":"2025-03-25T20:33:00.072Z","repository":{"id":38361926,"uuid":"134507907","full_name":"YuanTingHsieh/TF_TCN","owner":"YuanTingHsieh","description":"Tensorflow Temporal Convolutional Network","archived":false,"fork":false,"pushed_at":"2023-11-08T22:21:27.000Z","size":11380,"stargazers_count":82,"open_issues_count":0,"forks_count":39,"subscribers_count":6,"default_branch":"master","last_synced_at":"2023-11-10T07:38:22.717Z","etag":null,"topics":["convolutional-neural-networks","sequence-to-sequence","tensorflow"],"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/YuanTingHsieh.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}},"created_at":"2018-05-23T03:25:47.000Z","updated_at":"2023-11-10T07:08:19.000Z","dependencies_parsed_at":"2023-02-11T19:15:53.019Z","dependency_job_id":null,"html_url":"https://github.com/YuanTingHsieh/TF_TCN","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuanTingHsieh%2FTF_TCN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuanTingHsieh%2FTF_TCN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuanTingHsieh%2FTF_TCN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YuanTingHsieh%2FTF_TCN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YuanTingHsieh","download_url":"https://codeload.github.com/YuanTingHsieh/TF_TCN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222090797,"owners_count":16929472,"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":["convolutional-neural-networks","sequence-to-sequence","tensorflow"],"created_at":"2024-10-29T18:25:43.422Z","updated_at":"2024-10-29T18:25:44.023Z","avatar_url":"https://github.com/YuanTingHsieh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TF TCN\n*Tensorflow Temporal Convolutional Network*\n\nThis is an implementation of [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://arxiv.org/abs/1803.01271) in TensorFlow.\n\nI've verified that given same argument, my network has exactly same number of parameter as his model. It is able to reach the same loss/accuracy level in these problems, BUT sometimes it gets good result a little slower than the [original implementation in Torch](https://github.com/locuslab/TCN).\n\nThis repository mainly follows the structure of the original repo. And for illustration of different tasks, you could take a look at [keras TCN](https://github.com/philipperemy/keras-tcn). The author provides some nice figures there.\n\nSome codes are modified from [original implementation](https://github.com/locuslab/TCN), [keras TCN](https://github.com/philipperemy/keras-tcn), and [openai](https://github.com/openai/weightnorm/tree/master/tensorflow).\n\n\n## Domains and Datasets\nThis repository contains the benchmarks to the following tasks, with details explained in each sub-directory:\n\n  - The Adding Problem with various T (we evaluated on T=200, 400, 600)\n  - Copying Memory Task with various T (we evaluated on T=500, 1000, 2000)\n  - Sequential MNIST digit classification\n  - Permuted Sequential MNIST (based on Seq. MNIST, but more challenging)\n  - PennTreebank [SMALL] word-level language modeling (LM)\n    \n## Run\nIn the root directory of this repo, type the following to run different experiments\n```\npython3 -m [module_name] [args]\npython3 -m adding_problem.add_test [args]\npython3 -m copymem.copymem_test [args]\npython3 -m mnist_pixel.pmnist_test.py --epo 10\n```\n\n## References\n[1] Bai, Shaojie, J. Zico Kolter, and Vladlen Koltun. \"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling.\" arXiv preprint arXiv:1803.01271 (2018).\n[2] Salimans, Tim, and Diederik P. Kingma. \"Weight normalization: A simple reparameterization to accelerate training of deep neural networks.\" Advances in Neural Information Processing Systems. 2016.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyuantinghsieh%2Ftf_tcn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyuantinghsieh%2Ftf_tcn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyuantinghsieh%2Ftf_tcn/lists"}