{"id":13499131,"url":"https://github.com/Shathe/MNasNet-Keras-Tensorflow","last_synced_at":"2025-03-29T04:30:33.443Z","repository":{"id":111360179,"uuid":"144053166","full_name":"Shathe/MNasNet-Keras-Tensorflow","owner":"Shathe","description":"A Tensorflow Keras implementation (Graph and eager execution) of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile. ","archived":false,"fork":false,"pushed_at":"2020-03-05T14:54:38.000Z","size":224,"stargazers_count":99,"open_issues_count":1,"forks_count":29,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-10-31T17:39:15.708Z","etag":null,"topics":["architecture-search","deep-learning","eager-execution","keras","mnasnet","tensorflow"],"latest_commit_sha":null,"homepage":"","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/Shathe.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":"2018-08-08T18:32:26.000Z","updated_at":"2024-09-02T05:58:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"40ed7c3a-683a-4275-8fe5-c68f184663c3","html_url":"https://github.com/Shathe/MNasNet-Keras-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/Shathe%2FMNasNet-Keras-Tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shathe%2FMNasNet-Keras-Tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shathe%2FMNasNet-Keras-Tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shathe%2FMNasNet-Keras-Tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Shathe","download_url":"https://codeload.github.com/Shathe/MNasNet-Keras-Tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246140565,"owners_count":20729797,"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":["architecture-search","deep-learning","eager-execution","keras","mnasnet","tensorflow"],"created_at":"2024-07-31T22:00:29.622Z","updated_at":"2025-03-29T04:30:33.156Z","avatar_url":"https://github.com/Shathe.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["MNasNet"],"readme":"# MNasNet\n[Keras (Tensorflow) Implementation](https://github.com/Shathe/MNasNet-Keras-Tensorflow/blob/master/Mnasnet.py) of MNasNet and an example for training and evaluating it on the MNIST dataset. \nCheck also the [eager execution implementation](https://github.com/Shathe/MNasNet-Keras-Tensorflow/blob/master/MnasnetEager.py)\n\nAccording to the paper: [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://arxiv.org/pdf/1807.11626.pdf)\n\n## Requirement\n* Python 2.7+\n* Tensorflow-gpu 1.10\n\n## Train it\nTrain the [MNasNet model](https://github.com/Shathe/MNasNet-Keras-Tensorflow/blob/master/Mnasnet.py) on the MNIST dataset! just execute:\n```\npython train.py\n```\nFor checking and inspecting the Mnasnet model described in the paper, execute:\n```\npython Mnasnet.py\n```\n\n\n\n## Train it with eager execution\nTrain the [MNasNet (eager) model](https://github.com/Shathe/MNasNet-Keras-Tensorflow/blob/master/MnasnetEager.py) on the MNIST dataset! just execute:\n\n```\npython train_eager.py\n```\n\nThe eager execution implementation also outputs logs on Tensorboard. For its visualization:\n```\ntensorboard --logdir=train_log:./logs/train, test_log:./logs/test\n```\n\n## MnasNet for... Semantic Segmentation!\nIn this other repository, [FC-Mnasnet](https://github.com/Shathe/Semantic-Segmentation-Tensorflow-Eager) I added a decoder to the MnasNet architecture in order to turn it into a semantic segmentation model.\n\n\n\n![alt text](https://github.com/Shathe/MNasNet-Keras-Tensorflow/raw/master/mnasnet.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShathe%2FMNasNet-Keras-Tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FShathe%2FMNasNet-Keras-Tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShathe%2FMNasNet-Keras-Tensorflow/lists"}