{"id":15650528,"url":"https://github.com/ritchieng/resnet-tensorflow","last_synced_at":"2025-04-30T18:06:43.013Z","repository":{"id":81292383,"uuid":"76590824","full_name":"ritchieng/resnet-tensorflow","owner":"ritchieng","description":"Modular Residual Networks implemented in TensorFlow. Easily change hyperparameters in a few lines.","archived":false,"fork":false,"pushed_at":"2016-12-16T06:51:30.000Z","size":25,"stargazers_count":35,"open_issues_count":0,"forks_count":14,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-30T18:06:33.885Z","etag":null,"topics":["residual-network","tensorflow","tensorlayer"],"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/ritchieng.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-12-15T19:49:00.000Z","updated_at":"2024-11-16T07:35:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"a7bf66e0-578a-43cf-9019-ade95304f02d","html_url":"https://github.com/ritchieng/resnet-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/ritchieng%2Fresnet-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ritchieng%2Fresnet-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ritchieng%2Fresnet-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ritchieng%2Fresnet-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ritchieng","download_url":"https://codeload.github.com/ritchieng/resnet-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251758163,"owners_count":21638989,"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":["residual-network","tensorflow","tensorlayer"],"created_at":"2024-10-03T12:34:58.180Z","updated_at":"2025-04-30T18:06:42.983Z","avatar_url":"https://github.com/ritchieng.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Residual Networks in TensorFlow\n\n## Residual Network in TensorFlow\nThis entire code is implemented in pure TensorFlow and I have made it simple to run with different settings.\n\n## Simple Instructions\n- Running Training and Evaluation\n    - `python main.py`\n        - If you want to modify any parameters, you can use for example `python main.py --n_epoch==10`\n            - The default runs on CIFAR-10 dataset and this configuration is made for that.\n            - `n_epoch`: number of epochs\n                - Default `10`\n            - `n_batch`: batch size\n                - Default `64`\n            - `n_img_row`: dimension of image (row)\n                - Default `32`\n            - `n_img_col`: dimension of image (col)\n                - Default `32`\n            - `n_img_channels`: number of channels\n                - Default `3`\n            - `n_classes`: number of classes\n                - Default `10`\n            - `lr`: learning rate (momentum optimizer)\n                - Default `0.1`\n            - `n_resid_units`: number of residual units\n                - Default `5`\n            - `lr_schedule`: number of epoch for the learning rate to decrease by `lr_factor`\n                - Default `60`\n                - This multiplies the LR every 60 epochs by `lr_factor`.\n            - `lr_factor`: the factor for reducing LR\n                - Default `0.1`.\n        \n- Running TensorBoard\n    - Training logs\n        - `tensorboard --logdir=train_log`\n    - Evaluation logs\n        - `tensorboard --logdir=eval_log`\n    - You can use any path you want. \n        - If you encountered a `permission denied` error, you can easily solve it by changing the directory to `tmp/train_log`.\n        - I experienced this while running on Amazon AWS and it was solved with this fix.\n\n## Credits\n- The original model was obtained from the [official repository](https://github.com/tensorflow/models/tree/master/resnet) by TensorFlow.\n- The paper on [Residual Networks](https://arxiv.org/abs/1512.03385) on arXiv.org.\n\n## Dependencies\n- To simplify the code, I read the CIFAR dataset using [TensorLayer](https://github.com/zsdonghao/tensorlayer).\n    - Simply run `sudo pip install tensorlayer` and you are good to go.\n- TensorFlow v0.12\n    - If you would like to run this code in a few minutes on Amazon AWS, just use the open-source AMI [TFAMI.v3](https://github.com/ritchieng/tensorflow-aws-ami).\n\n## License\nMIT\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fritchieng%2Fresnet-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fritchieng%2Fresnet-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fritchieng%2Fresnet-tensorflow/lists"}