{"id":13499063,"url":"https://github.com/YixuanLi/densenet-tensorflow","last_synced_at":"2025-03-29T03:32:16.551Z","repository":{"id":89295704,"uuid":"68931654","full_name":"YixuanLi/densenet-tensorflow","owner":"YixuanLi","description":"DenseNet Implementation in Tensorflow","archived":false,"fork":false,"pushed_at":"2019-05-07T17:47:07.000Z","size":254,"stargazers_count":573,"open_issues_count":10,"forks_count":195,"subscribers_count":23,"default_branch":"master","last_synced_at":"2024-10-31T17:39:07.616Z","etag":null,"topics":["densenet","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YixuanLi.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2016-09-22T14:52:49.000Z","updated_at":"2024-10-25T14:13:40.000Z","dependencies_parsed_at":"2023-03-22T01:50:24.918Z","dependency_job_id":null,"html_url":"https://github.com/YixuanLi/densenet-tensorflow","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/YixuanLi%2Fdensenet-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YixuanLi%2Fdensenet-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YixuanLi%2Fdensenet-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YixuanLi%2Fdensenet-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YixuanLi","download_url":"https://codeload.github.com/YixuanLi/densenet-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135766,"owners_count":20729056,"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":["densenet","tensorflow"],"created_at":"2024-07-31T22:00:27.856Z","updated_at":"2025-03-29T03:32:16.274Z","avatar_url":"https://github.com/YixuanLi.png","language":"Python","funding_links":[],"categories":["Python","Papers\u0026Codes","Densely Connected Convolutional Networks"],"sub_categories":["DenseNet","Implementations"],"readme":"# DenseNet-tensorflow\nThis repository contains the tensorflow implementation for the paper [Densely Connected Convolutional Networks](http://arxiv.org/abs/1608.06993).\n\nThe code is developed based on Yuxin Wu's implementation of ResNet (https://github.com/ppwwyyxx/tensorpack/tree/master/examples/ResNet).\n\nCitation:\n\n     @inproceedings{huang2017densely,\n          title={Densely connected convolutional networks},\n          author={Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q },\n          booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n          year={2017}\n      }\n\n## Dependencies:\n\n+ Python 2 or 3\n+ TensorFlow \u003e= 1.0\n+ [Tensorpack] (https://github.com/ppwwyyxx/tensorpack)\n+ OpenCv-Python\n\n## Train a DenseNet (L=40, k=12) on CIFAR-10+ using\n\n```\npython cifar10-densenet.py\n```\nIn our experiment environment (cudnn v5.1, CUDA 7.5, one TITAN X GPU), the code runs with speed 5iters/s when batch size is set to be 64. The hyperparameters are identical to the original [torch implementation] (https://github.com/liuzhuang13/DenseNet).\n\n## Training curves on CIFAR-10+ (~5.77% after 300 epochs)\n\n![cifar10](cifar10.png)\n\n## Training curves on CIFAR-100+ (~26.36% after 300 epochs)\n\n![cifar100](cifar100.png)\n\n## Differences compared to the original [torch implementation] (https://github.com/liuzhuang13/DenseNet)\n+ Preprocessing is not channel-wise, instead we use mean and variances of images.\n+ There is no momentum and weight decay applied on the batch normalization parameters (gamma and beta), whereas torch vertison uses both momentum and weight decay on those.\n\n## Questions?\n\nPlease drop [me](http://www.cs.cornell.edu/~yli) a line if you have any questions!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYixuanLi%2Fdensenet-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYixuanLi%2Fdensenet-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYixuanLi%2Fdensenet-tensorflow/lists"}