{"id":13499107,"url":"https://github.com/markdtw/condensenet-tensorflow","last_synced_at":"2025-05-05T17:32:34.457Z","repository":{"id":93067253,"uuid":"119026624","full_name":"markdtw/condensenet-tensorflow","owner":"markdtw","description":"tensorflow implementation of CondenseNet: An Efficient DenseNet using Learned Group Convolutions","archived":false,"fork":false,"pushed_at":"2018-02-01T14:07:45.000Z","size":21,"stargazers_count":29,"open_issues_count":3,"forks_count":15,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-10-31T17:39:11.490Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/markdtw.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-01-26T08:34:42.000Z","updated_at":"2024-05-18T14:10:19.000Z","dependencies_parsed_at":"2023-06-04T15:15:07.549Z","dependency_job_id":null,"html_url":"https://github.com/markdtw/condensenet-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/markdtw%2Fcondensenet-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/markdtw%2Fcondensenet-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/markdtw%2Fcondensenet-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/markdtw%2Fcondensenet-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/markdtw","download_url":"https://codeload.github.com/markdtw/condensenet-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224457307,"owners_count":17314446,"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":[],"created_at":"2024-07-31T22:00:28.913Z","updated_at":"2024-11-13T13:41:23.889Z","avatar_url":"https://github.com/markdtw.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["CondenseNet"],"readme":"# CondenseNet tensorflow\nTensorflow implementation of [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://arxiv.org/abs/1711.09224). The code is tested with cifar10, *inference phase not implemented yet*.\n\n![Model architecture](https://i.imgur.com/f98IK2e.png)\n\nOfficial PyTorch implementation by @ShichenLiu [here](https://github.com/ShichenLiu/CondenseNet).\n\n## Prerequisites\n- Python 2.7+ (3.5+ is recommended)\n- [NumPy](http://www.numpy.org/)\n- [TensorFlow 1.0+](https://www.tensorflow.org/)\n\n\n## Data\n- [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)\n\n\n## Preparation\n- Go to `data/` folder and run `python2 generate_cifar10_tfrecords.py --data-dir=./cifar-10-data`. This code is directly borrowed from tensorflow official repo and have to be run with python 2.7+.\n\n\n## Train\nUse default parameters:\n```bash\npython main.py\n```\nCheck out tunable hyper-parameters:\n```bash\npython main.py --help\n```\nOther parameters including `stages, groups, condense factor, and growth rate` are in `experiment.py`.\n\n## Notes\n- Training for 300 epochs with the default settings reach testing accuracy 93.389% (paper report is 94.94%). There might be some details I didn't notice, feel free to point them out.\n- All the default parameters settings follow the paper/official pytorch implementation.\n- Current implmentations of standard group convolution and learned group convolution are very inefficient (a bunch of reshape, transpose and concat), looking for help to build much more efficient graph.\n- Evaluation phase (index select) has not been implemented yet, looking for potential help as well :D.\n- Issues are welcome!\n\n\n## Resources\n- [The paper](https://arxiv.org/abs/1711.09224).\n- [Official PyTorch Implementation](https://github.com/ShichenLiu/CondenseNet).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarkdtw%2Fcondensenet-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmarkdtw%2Fcondensenet-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarkdtw%2Fcondensenet-tensorflow/lists"}