{"id":13612726,"url":"https://github.com/yzwxx/vae-celebA","last_synced_at":"2025-04-13T12:32:34.669Z","repository":{"id":72877670,"uuid":"100266097","full_name":"yzwxx/vae-celebA","owner":"yzwxx","description":"Variational auto-encoder trained on celebA . All rights reserved.","archived":false,"fork":false,"pushed_at":"2017-12-14T14:34:14.000Z","size":2841,"stargazers_count":181,"open_issues_count":5,"forks_count":44,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-11-07T20:43:33.879Z","etag":null,"topics":["celeba-dataset","tensorflow","tensorlayer","variational-autoencoder","vggl16"],"latest_commit_sha":null,"homepage":null,"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/yzwxx.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":"2017-08-14T12:39:43.000Z","updated_at":"2024-09-20T18:55:02.000Z","dependencies_parsed_at":"2024-01-14T05:06:11.164Z","dependency_job_id":null,"html_url":"https://github.com/yzwxx/vae-celebA","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/yzwxx%2Fvae-celebA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzwxx%2Fvae-celebA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzwxx%2Fvae-celebA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzwxx%2Fvae-celebA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yzwxx","download_url":"https://codeload.github.com/yzwxx/vae-celebA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248714702,"owners_count":21149943,"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":["celeba-dataset","tensorflow","tensorlayer","variational-autoencoder","vggl16"],"created_at":"2024-08-01T20:00:33.583Z","updated_at":"2025-04-13T12:32:33.514Z","avatar_url":"https://github.com/yzwxx.png","language":"Python","funding_links":[],"categories":["7. (Variational) Autoencoders"],"sub_categories":["5.5 Spam Detection"],"readme":"# vae-celebA\nHereby we present plain VAE and modified VAE model, both of which are trained on celebA dataset to synthesize facial images.\n## Result:\n### plain VAE\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/vae_input.png\" width=\"300\"/\u003e  \n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/vae_recon.png\" width=\"300\"/\u003e  \n\u003c/div\u003e  \n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/vae_random.png\" width=\"300\"/\u003e  \n\u003c/div\u003e  \n\n### DFC-VAE\ninput image:  \n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/input.png\" width=\"300\"/\u003e  \n\u003c/div\u003e  \nreconstruction:  \n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/train_49_2914.png\" width=\"300\"/\u003e  \n\u003c/div\u003e  \nrandomly generation:  \n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/yzwxx/vae-celebA/blob/master/train_49_2914_random.png\" width=\"300\"/\u003e  \n\u003c/div\u003e  \n\nTo run the code, you are required to install Tensorflow and Tensorlayer on your machine. **[how to install Tensorlayer](https://github.com/zsdonghao/tensorlayer)**  \n\n## SOME NOTES\nThis is the code for the paper **[Deep Feature Consistent Variational Autoencoder](https://houxianxu.github.io/assets/project/dfcvae)**  \nIn loss function we used a vgg loss.Check this **[how to load and use a pretrained VGG-16?](https://github.com/zsdonghao/tensorlayer/blob/master/example/tutorial_vgg16.py)** if you have trouble reading vgg_loss.py.  \n\n## How to Run\nFirstly, download the [celebA dataset](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) and [VGG-16 weights](http://www.cs.toronto.edu/%7Efrossard/post/vgg16/).\nAfter installing all the third-party packages required, we can train the models by:  \n```python\npython train_vae.py # for plain VAE\npython train_dfc_vae.py # for DFC-VAE\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzwxx%2Fvae-celebA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyzwxx%2Fvae-celebA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzwxx%2Fvae-celebA/lists"}