{"id":13784425,"url":"https://github.com/ermongroup/mintnet","last_synced_at":"2025-05-08T01:20:35.950Z","repository":{"id":84088418,"uuid":"217955135","full_name":"ermongroup/mintnet","owner":"ermongroup","description":"MintNet: Building Invertible Neural Networks with Masked Convolutions","archived":false,"fork":false,"pushed_at":"2020-12-16T18:38:34.000Z","size":4558,"stargazers_count":39,"open_issues_count":4,"forks_count":8,"subscribers_count":6,"default_branch":"release","last_synced_at":"2025-03-31T16:09:06.409Z","etag":null,"topics":["density-estimation","flow-models","invertible-neural-networks","masked-convolutions","neurips2019"],"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/ermongroup.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":"2019-10-28T02:59:50.000Z","updated_at":"2024-09-30T11:02:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"3bd717e9-b9c1-47fe-b506-e9b6fb4b7030","html_url":"https://github.com/ermongroup/mintnet","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/ermongroup%2Fmintnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2Fmintnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2Fmintnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2Fmintnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ermongroup","download_url":"https://codeload.github.com/ermongroup/mintnet/tar.gz/refs/heads/release","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252979347,"owners_count":21835036,"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":["density-estimation","flow-models","invertible-neural-networks","masked-convolutions","neurips2019"],"created_at":"2024-08-03T19:00:42.962Z","updated_at":"2025-05-08T01:20:35.928Z","avatar_url":"https://github.com/ermongroup.png","language":"Python","funding_links":[],"categories":["📝 Publications \u003csmall\u003e(60)\u003c/small\u003e"],"sub_categories":[],"readme":"# MintNet: Building Invertible Neural Networks with Masked Convolutions\nThis repository contains the PyTorch implementation of our paper: \n[__MintNet: Building Invertible Neural Networks with Masked Convolutions__](https://arxiv.org/abs/1907.07945), _NeurIPS 2019_ .\nWe propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. \nThis leads to a rich set of invertible architectures, including those similar to \nResNets. Inversion is achieved with a locally convergent iterative procedure \nthat is parallelizable and very fast in practice. Additionally, \nthe determinant of the Jacobian can be computed analytically and efficiently, \nenabling their generative use as flow models.\n\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://github.com/chenlin9/Fully-Convolutional-Normalizing-Flows/blob/release/samples/MNIST_samples.png\" width=\"200\"\u003e\n\u003cimg src=\"https://github.com/chenlin9/Fully-Convolutional-Normalizing-Flows/blob/release/samples/CIFAR10_samples.png\" width=\"200\"\u003e\n\u003cimg src=\"https://github.com/chenlin9/Fully-Convolutional-Normalizing-Flows/blob/release/samples/ImageNet_samples.png\" width=\"200\"\u003e\n\u003c/p\u003e\n\n## Dependencies\n\nThe following are packages needed for running this repo.\n\n- PyTorch==1.1.0\n- tqdm\n- tensorboardX\n- Scipy\n- PyYAML\n- Numba\n\n## Running the experiments\n```bash\npython main.py --runner [runner name] --config [config file] --doc [experiment folder name]\n```\n\nHere `runner name` is one of the following:\n\n- `DensityEstimationRunner`. Experiments on MintNet density estimation.\n- `ClassificationRunner`. Experiments on MintNet classification.\n\n`config file` is the directory of some YAML file in `configs/`, and `experiment folder name` is the folder names in `run/`.\n\n\nFor example, if you want to train MintNet density estimation model on MNIST, just run\n\n```bash\npython main.py --runner DensityEstimationRunner --config mnist_density_config.yml\n```\n\n## Checkpoints\n\nCheckpoints for both density estimation and classification can be downloaded from [https://drive.google.com/file/d/12kGMMg0ivJI5y32hRouhZuddr9cJxfiR/view?usp=sharing](https://drive.google.com/file/d/12kGMMg0ivJI5y32hRouhZuddr9cJxfiR/view?usp=sharing)\n\nUnzip it to `\u003croot folder\u003e/run`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fermongroup%2Fmintnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fermongroup%2Fmintnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fermongroup%2Fmintnet/lists"}