{"id":25982544,"url":"https://github.com/aastopher/progressive_gan","last_synced_at":"2025-07-01T10:05:56.402Z","repository":{"id":62238545,"uuid":"558026700","full_name":"aastopher/Progressive_GAN","owner":"aastopher","description":"NVIDIA's Progressive GAN, implemented in PyTorch","archived":false,"fork":false,"pushed_at":"2022-11-16T19:41:45.000Z","size":363160,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-05T09:40:42.106Z","etag":null,"topics":["deep-learning","gan","generative-model","machine-learning","progressive-gan"],"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/aastopher.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":"2022-10-26T18:57:19.000Z","updated_at":"2022-11-21T13:08:07.000Z","dependencies_parsed_at":"2023-01-23T11:31:31.366Z","dependency_job_id":null,"html_url":"https://github.com/aastopher/Progressive_GAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/aastopher/Progressive_GAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastopher%2FProgressive_GAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastopher%2FProgressive_GAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastopher%2FProgressive_GAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastopher%2FProgressive_GAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aastopher","download_url":"https://codeload.github.com/aastopher/Progressive_GAN/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastopher%2FProgressive_GAN/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262941545,"owners_count":23388149,"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","gan","generative-model","machine-learning","progressive-gan"],"created_at":"2025-03-05T09:32:41.301Z","updated_at":"2025-07-01T10:05:56.381Z","avatar_url":"https://github.com/aastopher.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ProGAN (Progressive Generative Adversarial Network) trained on various image datasets\n\nThe purpose of this project is to expand knowledge of traditional GAN architectures by exploring NVIDIA's Progressive GAN research. [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://research.nvidia.com/publication/2018-04_progressive-growing-gans-improved-quality-stability-and-variation)\n\n### Install Dependencies\n* `pip install -r requirements.txt` - from project root\n\n### Initialize the Project\n* `python utils.py init` - download all logs for exploration then init empty models and results directory\n* You must **REMOVE** the logs folder this command will **NOT** overwrite an log files.\n\n### Download the Pre-trained models and results\n* `python utils.py download` - download the pre-trained model files and image sets.\n* Options = `[cars, cyber, dogs, faces, potatoes]`; default = `faces`\n* This command will NOT override existing models you must delete both `imgs` and `models` folders to download a new image and model set\n\n### Explore Tensorboard Results\n* `tensorboard --logdir logs` - to start the tensorboard and explore the current models training progress.\n\n### Train the model\n* **WARNING! This can overwrite existing models!** \n* `python train.py` - continue training or re-train model.\n* Changing the `LOAD_MODEL` global in `config.py`; chooses between re-training (`False`) or continuing training (`True`) for the model.\n\n### Generate Samples\n* `python utils.py sample` - generates sample images, by default this will generate 10 images at 64x64.\n* This command can be customized to generate a chosen amount of images at a chosen size `python utils.py sample \u003cnum_images\u003e \u003csize_factor\u003e`\n* Size factors: `0 = 4x4, 1 = 8x8, 2 = 16x16, 3 = 32x32, 4 = 64x64, 5 = 128x128, 6 = 256x256, 7 = 512x512, 8 = 1024x1024`\n\n### Preview Image Transforms\n* `python utils.py transform` - generates output images, by default this will output all batches at 128x128.\n* This command can be customized to generate a chosen amount of batches `python utils.py transform \u003cnum_batches\u003e`\n\n### Remove Duplicate Images\n* `python utils.py removedups` - remove duplicate images in the imgs folder using an image hash function.\n* This utility is designed to for cleaning custom image datasets of duplicate images\n* The `hash_size` for this function can be customized to have a looser hash criteria i.e accepting a larger difference between \"duplicates\"\n* This function will output how many duplicates have been removed and a path list for all duplicate images. **NOTE:** paths are not paired with duplicates.\n\n### References\n\n```\n@misc{https://doi.org/10.48550/arxiv.1701.07875,\n  doi = {10.48550/ARXIV.1701.07875},\n  url = {https://arxiv.org/abs/1701.07875},\n  author = {Arjovsky, Martin and Chintala, Soumith and Bottou, Léon},\n  keywords = {Machine Learning (stat.ML), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},\n  title = {Wasserstein GAN},\n  publisher = {arXiv},\n  year = {2017},\n  copyright = {arXiv.org perpetual, non-exclusive license}\n}\n```\n```\n@misc{https://doi.org/10.48550/arxiv.1704.00028,\n  doi = {10.48550/ARXIV.1704.00028},\n  url = {https://arxiv.org/abs/1704.00028},\n  author = {Gulrajani, Ishaan and Ahmed, Faruk and Arjovsky, Martin and Dumoulin, Vincent and Courville, Aaron},\n  keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},\n  title = {Improved Training of Wasserstein GANs},\n  publisher = {arXiv},\n  year = {2017},\n  copyright = {arXiv.org perpetual, non-exclusive license}\n}\n```\n```\n@misc{https://doi.org/10.48550/arxiv.1710.10196,\n  doi = {10.48550/ARXIV.1710.10196},\n  url = {https://arxiv.org/abs/1710.10196},\n  author = {Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},\n  keywords = {Neural and Evolutionary Computing (cs.NE), Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},\n  title = {Progressive Growing of GANs for Improved Quality, Stability, and Variation},\n  publisher = {arXiv},\n  year = {2017},\n  copyright = {arXiv.org perpetual, non-exclusive license}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faastopher%2Fprogressive_gan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faastopher%2Fprogressive_gan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faastopher%2Fprogressive_gan/lists"}