{"id":13499036,"url":"https://github.com/dblN/stochastic_depth_keras","last_synced_at":"2025-03-29T03:32:15.016Z","repository":{"id":215695099,"uuid":"55616394","full_name":"dblN/stochastic_depth_keras","owner":"dblN","description":"Keras implementation for \"Deep Networks with Stochastic Depth\" http://arxiv.org/abs/1603.09382","archived":false,"fork":false,"pushed_at":"2020-07-21T06:49:00.000Z","size":17,"stargazers_count":139,"open_issues_count":2,"forks_count":28,"subscribers_count":14,"default_branch":"master","last_synced_at":"2024-10-31T17:39:05.044Z","etag":null,"topics":[],"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/dblN.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":"2016-04-06T15:11:09.000Z","updated_at":"2024-01-04T16:04:03.000Z","dependencies_parsed_at":"2024-01-27T11:09:32.202Z","dependency_job_id":"54caa181-8e9e-4e71-bccb-954f43bc5f3f","html_url":"https://github.com/dblN/stochastic_depth_keras","commit_stats":null,"previous_names":["dbln/stochastic_depth_keras"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dblN%2Fstochastic_depth_keras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dblN%2Fstochastic_depth_keras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dblN%2Fstochastic_depth_keras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dblN%2Fstochastic_depth_keras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dblN","download_url":"https://codeload.github.com/dblN/stochastic_depth_keras/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135761,"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":[],"created_at":"2024-07-31T22:00:27.194Z","updated_at":"2025-03-29T03:32:14.736Z","avatar_url":"https://github.com/dblN.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","Deep Residual Learning"],"sub_categories":["Stochastic Depth ResNet","Implementations"],"readme":"[Deprecated]\nNo longer maintained\n(to catch up with the latest keras/theano/tensorflow but you'll get the idea of how to implement stochastic depth)\n\n# Deep Networks with Stochastic Depth\nKeras implementation for \"Deep Networks with Stochastic Depth\" http://arxiv.org/abs/1603.09382\n\nOriginal code(in lua/torch) is at https://github.com/yueatsprograms/Stochastic_Depth.\n\n\n## Usage\n\n1. Install [Theano](https://github.com/Theano/Theano) following its instruction.\n2. Install [Keras](https://github.com/fchollet/keras) (I use new API at `keras-1` branch)\n\n```\n$ cd keras\n$ git checkout keras-1\n$ python setup.py install\n```\n\n3. Just run `python train.py`\n\n\n## Known Issues\n\n- Error related to maximum recursion depth\n  - When the network is deep, there happens error saying it reaches to maximum recursion depth.\n  - You can resolve this issue by using `sys.setrecursionlimit(max_recursion_depth)`. You should increase `max_recursion_depth` until you get no error (Increasing this value might cause segmentation fault if you don't have enough memory).\n\n\n## Results\nCIFAR10\n\n- Number of layers == 50\n- (other configs are same as `train.py`)\n\n![results](https://cloud.githubusercontent.com/assets/10726958/14477064/904b573e-0146-11e6-865d-99fbd060486e.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FdblN%2Fstochastic_depth_keras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FdblN%2Fstochastic_depth_keras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FdblN%2Fstochastic_depth_keras/lists"}