{"id":13452802,"url":"https://github.com/melodyguan/enas","last_synced_at":"2025-03-23T21:35:03.712Z","repository":{"id":43088486,"uuid":"122676880","full_name":"melodyguan/enas","owner":"melodyguan","description":"TensorFlow Code for paper \"Efficient Neural Architecture Search via Parameter Sharing\"","archived":false,"fork":false,"pushed_at":"2019-06-18T14:02:10.000Z","size":3980,"stargazers_count":1585,"open_issues_count":85,"forks_count":390,"subscribers_count":76,"default_branch":"master","last_synced_at":"2024-08-01T08:06:41.144Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1802.03268","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/melodyguan.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}},"created_at":"2018-02-23T21:56:49.000Z","updated_at":"2024-07-24T20:47:05.000Z","dependencies_parsed_at":"2022-09-24T14:50:52.255Z","dependency_job_id":null,"html_url":"https://github.com/melodyguan/enas","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/melodyguan%2Fenas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/melodyguan%2Fenas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/melodyguan%2Fenas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/melodyguan%2Fenas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/melodyguan","download_url":"https://codeload.github.com/melodyguan/enas/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221918516,"owners_count":16901640,"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":"2024-07-31T08:00:23.255Z","updated_at":"2024-10-28T19:31:00.578Z","avatar_url":"https://github.com/melodyguan.png","language":"Python","funding_links":[],"categories":["Automated Deep Learning","Neural architecture search","Neural Architecture Search","Neural Architecture Search (NAS)","AutoML","1.) Neural Architecture Search","Projects"],"sub_categories":["Reinforcement Learning","**[Papers]**","Distributed Frameworks"],"readme":"# Efficient Neural Architecture Search via Parameter Sharing\n\nAuthors' implementation of \"Efficient Neural Architecture Search via Parameter Sharing\" (2018) in TensorFlow.\n\nIncludes code for CIFAR-10 image classification and Penn Tree Bank language modeling tasks.\n\nPaper: https://arxiv.org/abs/1802.03268\n\nAuthors: Hieu Pham*, Melody Y. Guan*, Barret Zoph, Quoc V. Le, Jeff Dean\n\n_This is not an official Google product._\n\n## Penn Treebank\n\n**IMPORTANT ERRATA**: The implementation of Language Model on this repository is wrong. Please do not use it. The correct implementation is at the [new repository](https://github.com/google-research/google-research/tree/master/enas_lm). We apologize for the inconvenience.\n\n## CIFAR-10\n\nTo run the experiments on CIFAR-10, please first download the [dataset](https://www.cs.toronto.edu/~kriz/cifar.html). Again, all hyper-parameters are specified in the scripts that we descibe below.\n\nTo run the ENAS experiments on the _macro search space_ as described in our paper, please use the following scripts:\n```\n./scripts/cifar10_macro_search.sh\n./scripts/cifar10_macro_final.sh\n```\n\nA macro architecture for a neural network with `N` layers consists of `N` parts, indexed by `1, 2, 3, ..., N`. Part `i` consists of:\n\n* A number in `[0, 1, 2, 3, 4, 5]` that specifies the operation at layer `i`-th, corresponding to `conv_3x3`, `separable_conv_3x3`, `conv_5x5`, `separable_conv_5x5`, `average_pooling`, `max_pooling`.\n* A sequence of `i - 1` numbers, each is either `0` or `1`, indicating whether a skip connection should be formed from a the corresponding past layer to the current layer.\n\nA concrete example can be found in our script `./scripts/cifar10_macro_final.sh`.\n\nTo run the ENAS experiments on the _micro search space_ as described in our paper, please use the following scripts:\n```\n./scripts/cifar10_micro_search.sh\n./scripts/cifar10_micro_final.sh\n```\n\nA micro cell with `B + 2` blocks can be specified using `B` blocks, corresponding to blocks numbered `2, 3, ..., B+1`, each block consists of `4` numbers\n```\nindex_1, op_1, index_2, op_2\n```\nHere, `index_1` and `index_2` can be any previous index. `op_1` and `op_2` can be `[0, 1, 2, 3, 4]`, corresponding to `separable_conv_3x3`, `separable_conv_5x5`, `average_pooling`, `max_pooling`, `identity`.\n\nA micro architecture can be specified by two sequences of cells concatenated after each other, as shown in our script `./scripts/cifar10_micro_final.sh`\n\n## Citations\n\nIf you happen to use our work, please consider citing our paper.\n```\n@inproceedings{enas,\n  title     = {Efficient Neural Architecture Search via Parameter Sharing},\n  author    = {Pham, Hieu and\n               Guan, Melody Y. and\n               Zoph, Barret and\n               Le, Quoc V. and\n               Dean, Jeff\n  },\n  booktitle = {ICML},\n  year      = {2018}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmelodyguan%2Fenas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmelodyguan%2Fenas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmelodyguan%2Fenas/lists"}