{"id":15338465,"url":"https://github.com/srowen/autoenc-neurons","last_synced_at":"2025-10-10T14:31:45.867Z","repository":{"id":77221045,"uuid":"98091341","full_name":"srowen/autoenc-neurons","owner":"srowen","description":"Simple example of Keras, TensorFlow and autoencoders applied to text","archived":true,"fork":false,"pushed_at":"2018-05-30T23:16:05.000Z","size":1725,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-28T03:35:10.053Z","etag":null,"topics":["autoencoder","gpu","gutenberg","jane-austen","keras","neurons","tensorflow"],"latest_commit_sha":null,"homepage":"","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/srowen.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":"2017-07-23T10:46:02.000Z","updated_at":"2023-01-28T20:16:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"b9b0f1b7-b4a1-47a1-8daf-1db198013c4a","html_url":"https://github.com/srowen/autoenc-neurons","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/srowen/autoenc-neurons","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/srowen%2Fautoenc-neurons","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/srowen%2Fautoenc-neurons/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/srowen%2Fautoenc-neurons/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/srowen%2Fautoenc-neurons/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/srowen","download_url":"https://codeload.github.com/srowen/autoenc-neurons/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/srowen%2Fautoenc-neurons/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279004176,"owners_count":26083688,"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","status":"online","status_checked_at":"2025-10-10T02:00:06.843Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["autoencoder","gpu","gutenberg","jane-austen","keras","neurons","tensorflow"],"created_at":"2024-10-01T10:25:20.097Z","updated_at":"2025-10-10T14:31:45.861Z","avatar_url":"https://github.com/srowen.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# autoenc-neurons (work in progress)\n\nAn experiment with convolutional autoencoders as applied to text, and exploring what the\n'neurons' in the convolutional layers respond to.\n\n## Running\n\nNote that if you do not have GPUs, you will need to edit the script to install `tensorflow` \ninstead of `tensorflow-gpu`, and change `gpu_count` to 0.\n\n```bash\npython3 autoenc-neurons.py\n```\n\nThis will start model training and then produce output, at last, like this:\n\n![](docs/img/neuron_output.png)\n\nThe output contains several lines from the text, repeated several times. In each\nstanza, the letters are shaded according to the activation that it causes a particular neuron\n(darker means more active). This is repeated for several neurons.\n\n\n## References\n\nThe source text is The Complete Project Gutenberg Works of Jane Austen:                       \nhttp://www.gutenberg.org/files/31100/31100.txt\n\nFor more on convolutional autoencoders in Keras, see:\nhttps://blog.keras.io/building-autoencoders-in-keras.html","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsrowen%2Fautoenc-neurons","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsrowen%2Fautoenc-neurons","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsrowen%2Fautoenc-neurons/lists"}