{"id":13499108,"url":"https://github.com/titu1994/Keras-NASNet","last_synced_at":"2025-03-29T03:32:24.104Z","repository":{"id":150946843,"uuid":"111054933","full_name":"titu1994/Keras-NASNet","owner":"titu1994","description":"\"NASNet\" models in Keras 2.0+ with weights","archived":false,"fork":false,"pushed_at":"2018-05-17T06:22:34.000Z","size":3724,"stargazers_count":198,"open_issues_count":9,"forks_count":64,"subscribers_count":19,"default_branch":"master","last_synced_at":"2025-03-15T04:42:23.739Z","etag":null,"topics":["keras","nasnet-models","tensorflow"],"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/titu1994.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}},"created_at":"2017-11-17T03:50:57.000Z","updated_at":"2025-01-03T12:57:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"9879f05d-6e11-474d-af28-1aa7ad69d80c","html_url":"https://github.com/titu1994/Keras-NASNet","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FKeras-NASNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FKeras-NASNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FKeras-NASNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FKeras-NASNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/titu1994","download_url":"https://codeload.github.com/titu1994/Keras-NASNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135765,"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":["keras","nasnet-models","tensorflow"],"created_at":"2024-07-31T22:00:28.943Z","updated_at":"2025-03-29T03:32:22.746Z","avatar_url":"https://github.com/titu1994.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["NasNet"],"readme":"# Keras Neural Architecture Search Network (NASNet)\nAn implementation of \"NASNet\" models from the paper [Learning Transferable Architectures for Scalable Image Recognitio](https://arxiv.org/abs/1707.07012) in Keras 2.0+.\n\nBased on the models described in the [TFSlim implementation](https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet) and some modules from the [TensorNets implementation](https://github.com/taehoonlee/tensornets/blob/master/tensornets/nasnets.py)\n\nWeights have been ported over from the official [NASNet Tensorflow repository](https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet).\n\nSince CIFAR weights are not provided, and I don't have the resources to train such large models on CIFAR, those weights will not be provided. External help is appreciated.\n\n# Usage\nAll types of NASNet models can be built. In addition, `NASNet Large - NASNet (6 @ 4032)` and `NASNet Mobile - NASNet (4 @ 1056)` are prebuilt and provided as `NASNetLarge` and `NASNetMobile`.\n\n## Building a speficific NASNet model\n\n```python\nfrom nasnet import NASNet\n\n# the parameters for NASNetLarge\nmodel = NASNet(input_shape=(331, 331, 3),\n           penultimate_filters=4032,\n           nb_blocks=6,\n           stem_filters=96,\n           skip_reduction=True,\n           use_auxilary_branch=False,\n           filters_multiplier=2,\n           dropout=0.5,\n           classes=1000)\n```\n\n## Using Pre-built NASNet models\n```python\nfrom nasnet import NASNetLarge, NASNetMobile\n\nmodel = NASNetLarge(input_shape=(331, 331, 3), dropout=0.5)\n```\n\n# Network Overview\n\n\u003cimg src=\"https://github.com/titu1994/Keras-NASNet/blob/master/images/nasnet_mobile.png?raw=true\" height=100% width=100%\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftitu1994%2FKeras-NASNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftitu1994%2FKeras-NASNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftitu1994%2FKeras-NASNet/lists"}