{"id":19794701,"url":"https://github.com/kuleshov/deep-learning-models","last_synced_at":"2025-05-01T02:31:06.608Z","repository":{"id":73200481,"uuid":"75018376","full_name":"kuleshov/deep-learning-models","owner":"kuleshov","description":"Implementations of popular deep learning models in Theano+Lasagne","archived":false,"fork":false,"pushed_at":"2017-07-12T03:13:07.000Z","size":83,"stargazers_count":24,"open_issues_count":0,"forks_count":20,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-06T08:04:33.621Z","etag":null,"topics":[],"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/kuleshov.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}},"created_at":"2016-11-28T22:04:46.000Z","updated_at":"2024-02-12T23:51:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"857313f4-96aa-4510-80fe-6dd9a819826f","html_url":"https://github.com/kuleshov/deep-learning-models","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/kuleshov%2Fdeep-learning-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuleshov%2Fdeep-learning-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuleshov%2Fdeep-learning-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuleshov%2Fdeep-learning-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kuleshov","download_url":"https://codeload.github.com/kuleshov/deep-learning-models/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251812323,"owners_count":21647885,"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":"2024-11-12T07:13:56.505Z","updated_at":"2025-05-01T02:31:06.359Z","avatar_url":"https://github.com/kuleshov.png","language":"Python","funding_links":[],"categories":["Table of Contents"],"sub_categories":[],"readme":"Deep Learning Model Zoo\n=======================\n\nThis repository contains implementations of various deep learning algorithms in Theano/Lasagne.\n\n## Running a model\n\nTo run a model, you may use the `run.py` launch script.\n\n```\npython run.py train \\\n  --dataset \u003cdataset\u003e \\\n  --model \u003cepochs\u003e \\\n  --alg \u003copt_alg\u003e \\\n  --n_batch \u003cbatch_size\u003e \\\n  --lr \u003clearning_rate\u003e \\\n  -e \u003cnum_epochs\u003e \\\n  -l \u003clog_name\u003e\n```\n\nAlternatively, you may use the `Makefile` included in the root dir; typing `make train` will start training. There are also several additional parameters that can be configured inside the `Makefile`.\n\nThe model will periodically save its weights and report training/validation losses in the logfile.\n\n## Algorithms\n\nThe following algorithms are available.\n\n### Supervised learning models\n\n* `softmax`: simple softmax classifier\n* `mlp`: multilayer perceptron\n* `cnn`: convolutional neural network; solves `mnist` and achieves reasonably good accuracy on `cifar10`\n* `resnet`: small residual network; achieves an accuracy in the 80's on `cifar10`\n\n### Semi-supervised models\n\n* `ssdadgm`: semi-supervised deep generative models (in progress)\n\n### Unsupervised models\n\n* `vae`: variational autoencoder\n* `convvae`: convolutional variational autoencoder\n* `sbn`: vae with discrete latent variables, trained with neural variational inference (reduces to sigmoid belief network)\n* `adgm`: auxiliary deep generative model (unsupervised version)\n* `convadgm`: convolutional auxiliary deep generative model (unsupervised version)\n* `dadgm`: discrete-variable auxiliary deep generative model (unsupervised version, also trained with NVIL)\n* `dcgan`: small deep convolutional generative adversarial network (tested on mnist)\n\n## Datasets\n\nThe following datasets are currently available:\n\n* `cifar10`: color images divided into 10 classes (32x32x3)\n* `mnist`: standard handwritten digits dataset (28x28)\n* `digits`: sklearn digits dataset (8x8); can be used for quick debugging on a CPU\n\n## Optimization methods\n\nCurrently, we may train the models using:\n\n* `sgd`: standard stochastic gradient descent\n* `adam`: the Adam optimizer\n\n## Feedback\n\nSend feedback to [Volodymyr Kuleshov](http://www.stanford.edu/~kuleshov). Some models contain snippets from other users' repositories; let me know if I forgot to cite anyone.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuleshov%2Fdeep-learning-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkuleshov%2Fdeep-learning-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuleshov%2Fdeep-learning-models/lists"}