{"id":13869748,"url":"https://github.com/rosinality/glow-pytorch","last_synced_at":"2025-04-28T13:08:41.487Z","repository":{"id":41274765,"uuid":"140671425","full_name":"rosinality/glow-pytorch","owner":"rosinality","description":"PyTorch implementation of Glow","archived":false,"fork":false,"pushed_at":"2021-11-20T23:21:48.000Z","size":12315,"stargazers_count":534,"open_issues_count":32,"forks_count":98,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-04-28T13:08:35.430Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/rosinality.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}},"created_at":"2018-07-12T06:34:34.000Z","updated_at":"2025-04-17T06:44:40.000Z","dependencies_parsed_at":"2022-08-02T23:15:20.683Z","dependency_job_id":null,"html_url":"https://github.com/rosinality/glow-pytorch","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/rosinality%2Fglow-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rosinality%2Fglow-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rosinality%2Fglow-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rosinality%2Fglow-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rosinality","download_url":"https://codeload.github.com/rosinality/glow-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251319607,"owners_count":21570427,"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":"2024-08-05T20:01:15.088Z","updated_at":"2025-04-28T13:08:41.186Z","avatar_url":"https://github.com/rosinality.png","language":"Python","funding_links":[],"categories":["Python","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# glow-pytorch\nPyTorch implementation of Glow, Generative Flow with Invertible 1x1 Convolutions (https://arxiv.org/abs/1807.03039)\n\nUsage:\n\n\u003e python train.py PATH\n\nas trainer uses ImageFolder of torchvision, input directory should be structured like this even when there are only 1 classes. (Currently this implementation does not incorporate class classification loss.)\n\n\u003e PATH/class1 \u003cbr/\u003e\n\u003e PATH/class2 \u003cbr/\u003e\n\u003e ...\n\n## Notes\n\n![Sample](sample.png)\n\nI have trained model on vanilla celebA dataset. Seems like works well. I found that learning rate (I have used 1e-4 without scheduling), learnt prior, number of bits (in this cases, 5), and using sigmoid function at the affine coupling layer instead of exponential function is beneficial to training a model.\n\nIn my cases, LU decomposed invertible convolution was much faster than plain version. So I made it default to use LU decomposed version.\n\n![Progression of samples](progression.gif)\n\nProgression of samples during training. Sampled once per 100 iterations during training.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frosinality%2Fglow-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frosinality%2Fglow-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frosinality%2Fglow-pytorch/lists"}