{"id":27373401,"url":"https://github.com/yassa9/doodlevae","last_synced_at":"2026-05-15T22:39:18.282Z","repository":{"id":285692580,"uuid":"958934926","full_name":"yassa9/doodleVAE","owner":"yassa9","description":"Yet another disentangled VAE ... but for quick drawing doodles","archived":false,"fork":false,"pushed_at":"2025-04-02T06:09:02.000Z","size":1200,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-13T11:14:33.810Z","etag":null,"topics":["deep-learning","doodle","face","generative-ai","latent-space","latent-variable-models","ml","nn","pytorch","quickdr","quickdraw-dataset","vae","vae-pytorch"],"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/yassa9.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-04-02T02:13:46.000Z","updated_at":"2025-04-02T06:28:04.000Z","dependencies_parsed_at":"2025-04-02T07:22:55.918Z","dependency_job_id":"1e9d0b30-e08a-4f45-bb89-4221a7be1ae9","html_url":"https://github.com/yassa9/doodleVAE","commit_stats":null,"previous_names":["yassa9/doodlevae"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassa9%2FdoodleVAE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassa9%2FdoodleVAE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassa9%2FdoodleVAE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassa9%2FdoodleVAE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yassa9","download_url":"https://codeload.github.com/yassa9/doodleVAE/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248703197,"owners_count":21148118,"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","doodle","face","generative-ai","latent-space","latent-variable-models","ml","nn","pytorch","quickdr","quickdraw-dataset","vae","vae-pytorch"],"created_at":"2025-04-13T11:14:36.764Z","updated_at":"2026-05-15T22:39:18.254Z","avatar_url":"https://github.com/yassa9.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ca id=\"readme-top\"\u003e\u003c/a\u003e\n\n\u003cbr /\u003e\n\u003cdiv align=\"center\"\u003e\n  \u003c!-- \u003ca href=\"https://github.com/yassa9/doodleVAE\"\u003e\n    \u003cimg src=\"images/logo.jpg\" alt=\"Logo\" width=\"80\" height=\"80\"\u003e\n  \u003c/a\u003e --\u003e\n\n  \u003ch1 align=\"center\" style=\"font-size: 60px;\"\u003edoodleVAE\u003c/h1\u003e\n\n  \u003cp align=\"center\"\u003e\n    Yet another disentangled VAE ... but for quick drawing doodles.\n    \u003cbr /\u003e\n\n[![GIF shot][product-screenshot]](https://github.com/yassa9/doodleVAE)\n\n  \u003c/p\u003e\n\u003c/div\u003e\n\n\n\u003c!-- ABOUT THE PROJECT --\u003e\n## The Model\n\nThis project implements a `Variational Autoencoder (VAE)` trained to generate hand-drawn doodles. It learns a compressed latent representation of doodles from the `Quick, Draw! dataset` and uses it to generate new, human-like sketches.\n\n### The model consists of:\n\n- [x] Convolutional encoder that compresses input images into a latent vector\n- [x] Reparameterization layer to sample from the latent space\n- [x] Convolutional decoder that reconstructs images from latent vectors\n- [x] Latent space exploration, saved as an animation\n- [x] Loss plotting\n\nThe training pipeline supports configurable hyperparameters (e.g. latent dimension, beta, batch size, epochs) through a configuration file or command-line arguments.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eBack Top\u003c/a\u003e)\u003c/p\u003e\n\n\u003c!-- ### Built With --\u003e\n\n\u003c!-- * [![Python][python]][python-url] --\u003e\n\u003c!-- * [![PyTorch][pytorch]][pytorch-url] --\u003e\n\u003c!-- * [![Numpy][numpy]][numpy-url] --\u003e\n\u003c!-- * [![Matplotlib][matplotlib]][matplotlib-url] --\u003e\n\u003c!-- * [![openCV][opencv]][opencv-url] --\u003e\n\n\u003c!-- \u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eBack Top\u003c/a\u003e)\u003c/p\u003e --\u003e\n\n## Getting Started\n\nFollow these steps to set up and run the project locally.\n\n### Prerequisites\n\nEnsure you have Python installed (\u003e= 3.8 recommended).  \nYou can install it from [python.org](https://www.python.org/).\n\n### Installation\n\n1. **Clone the repository**\n   ```bash\n   git clone https://github.com/yassa9/doodleVAE.git\n   cd doodleVAE\n   ```\n\n2. **Install dependencies**\n\n   You can install everything with pip:\n   ```bash\n   pip install torch torchvision matplotlib numpy\n   ```\n\n3. **Prepare your dataset**\n\n   - Provide a file `\u003cfile\u003e.npy` path using `--data-path`.\n   - You can get data from [Quick, Draw!](https://github.com/googlecreativelab/quickdraw-dataset).\n\n### Training\n\nTo train the model, run:\n\n```bash\npython train.py --data-path path/to/\u003cfile\u003e.npy\n```\n\nYou can customize training with command-line arguments:\n\n```bash\npython train.py --data-path cat.npy --epochs 50 --latent-dim 20 --beta 4\n```\n\n| Argument        | Description                             |\n|----------------|-----------------------------------------|\n| `--epochs`      | Number of training epochs               |\n| `--batch-size`  | Training batch size                     |\n| `--latent-dim`  | Dimensionality of latent space          |\n| `--beta`        | Beta value for KL divergence term       |\n| `--lr`          | Learning rate                           |\n| `--save-dir`    | Directory to save model and plots       |\n| `--no-explore`  | Skip final latent interpolation animation |\n\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eBack Top\u003c/a\u003e)\u003c/p\u003e\n\n\n\n\u003c!-- MARKDOWN LINKS \u0026 IMAGES --\u003e\n[product-screenshot]: images/gifshot.gif\n\n[python]: https://img.shields.io/badge/python-3670A0?style=for-the-badge\u0026logo=python\u0026logoColor=ffdd54\n[python-url]: https://www.python.org/\n[pytorch]: https://img.shields.io/badge/PyTorch-%23EE4C2C.svg?style=for-the-badge\u0026logo=PyTorch\u0026logoColor=white\n[pytorch-url]: https://pytorch.org/\n[numpy]: https://img.shields.io/badge/numpy-%23013243.svg?style=for-the-badge\u0026logo=numpy\u0026logoColor=white\n[numpy-url]: https://numpy.org/\n[matplotlib]: https://img.shields.io/badge/Matplotlib-%23ffffff.svg?style=for-the-badge\u0026logo=Matplotlib\u0026logoColor=black\n[matplotlib-url]: https://matplotlib.org/\n[opencv]: https://img.shields.io/badge/opencv-%23white.svg?style=for-the-badge\u0026logo=opencv\u0026logoColor=white\n[opencv-url]: https://opencv.org/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyassa9%2Fdoodlevae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyassa9%2Fdoodlevae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyassa9%2Fdoodlevae/lists"}