{"id":19853123,"url":"https://github.com/unixpickle/anynet","last_synced_at":"2025-05-02T00:31:54.342Z","repository":{"id":57479933,"uuid":"79572807","full_name":"unixpickle/anynet","owner":"unixpickle","description":"Framework for artificial neural networks","archived":false,"fork":false,"pushed_at":"2017-09-09T17:30:53.000Z","size":198,"stargazers_count":34,"open_issues_count":0,"forks_count":7,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-06T20:23:59.070Z","etag":null,"topics":["deep-learning","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Go","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/unixpickle.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}},"created_at":"2017-01-20T15:52:35.000Z","updated_at":"2024-08-12T19:27:16.000Z","dependencies_parsed_at":"2022-09-26T17:41:33.896Z","dependency_job_id":null,"html_url":"https://github.com/unixpickle/anynet","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/unixpickle%2Fanynet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unixpickle%2Fanynet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unixpickle%2Fanynet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unixpickle%2Fanynet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/unixpickle","download_url":"https://codeload.github.com/unixpickle/anynet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251966431,"owners_count":21672666,"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":["deep-learning","machine-learning"],"created_at":"2024-11-12T14:05:50.528Z","updated_at":"2025-05-02T00:31:49.319Z","avatar_url":"https://github.com/unixpickle.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# anynet [![GoDoc](https://godoc.org/github.com/unixpickle/anynet?status.svg)](https://godoc.org/github.com/unixpickle/anynet)\n\n**anynet** is a [neural network](https://en.wikipedia.org/wiki/Artificial_neural_network) framework based on [anydiff](https://github.com/unixpickle/anydiff) and [anyvec](https://github.com/unixpickle/anyvec).\n\n# Supported features\n\n*anynet* ships with a ton of built-in features:\n\n * Feed-forward neural networks\n   * Fully-connected layers\n   * Convolution\n   * Dropout\n   * Max/Mean pooling\n   * Batch normalization\n   * Residual connections\n   * Image scaling\n   * Image padding\n * Recurrent neural networks\n   * LSTM\n   * Bidirectional RNNs\n   * npRNN and IRNN (vanilla RNNs with ReLU activations)\n * Training setups\n   * Vector-to-vector (standard feed-forward)\n   * Sequence-to-sequence (standard RNN)\n   * Sequence-to-vector\n   * Connectionist Temporal Classification\n * Miscellaneous\n   * Gumbel Softmax\n\nPlenty of stuff is missing from the above list. Luckily, it's easy to write new APIs on top of *anynet*. Here is a non-exhaustive list of packages that work with *anynet*:\n\n * [unixpickle/anyrl](https://github.com/unixpickle/anyrl) - deep reinforcement learning\n * [unixpickle/lazyseq](https://github.com/unixpickle/lazyseq) - memory-efficient RNNs\n * [unixpickle/attention](https://github.com/unixpickle/attention) - attention mechanisms\n * [unixpickle/rwa](https://github.com/unixpickle/rwa) - a new attention-based RNN architecture\n\n# TODO\n\nHere are some minor things I'd like to get done at some point. None of these are very urgent, as *anynet* is already complete for the most part.\n\n * anyrnn\n   * Tests comparing LSTM outputs to another implementation\n   * GRU (gated recurrent units)\n * anysgd\n   * Gradient clipping\n   * Marshalling for RMSProp\n   * Marshalling for Momentum\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funixpickle%2Fanynet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funixpickle%2Fanynet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funixpickle%2Fanynet/lists"}