# hVAE - backbone
This repository contains:
- customizable backbone implementation of hVAE
- reuseable hVAE components such as blocks, layers, losses, etc.
- training, evaluation and analyzation scripts
- checkpoint handling (using [Weights & Biases](https://wandb.ai/site))
## Installation
```bash
pip install hvae_backbone
```
## Usage
This repository is intended to be used as a backend package.
Please refer to [hvae template](https://github.com/lacykaltgr/hvae) repository for usage instructions.
## Project Structure
```
├── hvae_backbone
│ ├── elements
│ │ ├── __init__.py
│ │ ├── data_preproc.py # Modules for data preprocessing
│ │ ├── dataset.py # Base dataset class
│ │ ├── distributions.py # Distributions, distributions generation
│ │ ├── layers.py # Layers for building models
│ │ ├── losses.py # Loss functions
│ │ ├── nets.py # Network architectures
│ │ ├── optimizers.py # Optimizers
│ │ ├── schedules.py # Schedules e.g. LR, KL weight
│ ├── __init__.py # package level scripts
│ ├── analysis.py # Analysis tools for trained models
│ ├── block.py # Blocks for building hierarchical models
│ ├── checkpoint.py # Checkpoint handling (save, load)
│ ├── functional.py # Functional scripts (training, loss, etc.)
│ ├── hvae.py # General hVAE class
│ ├── sequence.py # General sequential hVAE class
│ ├── utils.py # Utility functions
```
# TODO:
- callbacks
- preprocessing
- sample vs rsmaple blokkoknál (SimpleGenBlock)
- weight initialization
Raw data
{
"_id": null,
"home_page": "https://github.com/lacykaltgr/hvae-backbone",
"name": "hvae-backbone",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "vae,hierarchical vae,generative model",
"author": "L\u00e1szl\u00f3 Freund",
"author_email": "freundl0509@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/33/27/acf659493dc6ab1df92c82decf649d928794886b8c22b55d924172a092ae/hvae_backbone-0.1.126.tar.gz",
"platform": null,
"description": "# hVAE - backbone\n\nThis repository contains:\n- customizable backbone implementation of hVAE\n- reuseable hVAE components such as blocks, layers, losses, etc.\n- training, evaluation and analyzation scripts\n- checkpoint handling (using [Weights & Biases](https://wandb.ai/site))\n\n\n## Installation\n```bash\npip install hvae_backbone\n```\n\n## Usage\nThis repository is intended to be used as a backend package. \nPlease refer to [hvae template](https://github.com/lacykaltgr/hvae) repository for usage instructions.\n\n\n## Project Structure\n\n```\n\u251c\u2500\u2500 hvae_backbone\n\u2502 \u251c\u2500\u2500 elements\n\u2502 \u2502 \u251c\u2500\u2500 __init__.py \n\u2502 \u2502 \u251c\u2500\u2500 data_preproc.py # Modules for data preprocessing\n\u2502 \u2502 \u251c\u2500\u2500 dataset.py # Base dataset class\n\u2502 \u2502 \u251c\u2500\u2500 distributions.py # Distributions, distributions generation\n\u2502 \u2502 \u251c\u2500\u2500 layers.py # Layers for building models\n\u2502 \u2502 \u251c\u2500\u2500 losses.py # Loss functions\n\u2502 \u2502 \u251c\u2500\u2500 nets.py # Network architectures\n\u2502 \u2502 \u251c\u2500\u2500 optimizers.py # Optimizers\n\u2502 \u2502 \u251c\u2500\u2500 schedules.py # Schedules e.g. LR, KL weight\n\u2502 \u251c\u2500\u2500 __init__.py # package level scripts\n\u2502 \u251c\u2500\u2500 analysis.py # Analysis tools for trained models\n\u2502 \u251c\u2500\u2500 block.py # Blocks for building hierarchical models\n\u2502 \u251c\u2500\u2500 checkpoint.py # Checkpoint handling (save, load)\n\u2502 \u251c\u2500\u2500 functional.py # Functional scripts (training, loss, etc.)\n\u2502 \u251c\u2500\u2500 hvae.py # General hVAE class\n\u2502 \u251c\u2500\u2500 sequence.py # General sequential hVAE class\n\u2502 \u251c\u2500\u2500 utils.py # Utility functions\n```\n\n\n# TODO:\n- callbacks\n- preprocessing\n- sample vs rsmaple blokkokn\u00e1l (SimpleGenBlock)\n- weight initialization\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Universal and customizable implementation of the Hierarchical Variational Autoencoder architecture.",
"version": "0.1.126",
"project_urls": {
"Homepage": "https://github.com/lacykaltgr/hvae-backbone"
},
"split_keywords": [
"vae",
"hierarchical vae",
"generative model"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2f736cafcbbeda700bb9b079ab88091f0574a2c1b14ea401e9a2122fb9385787",
"md5": "6ed91d9855ff9927fd339180f045236a",
"sha256": "c912e13a4d9214a05b937b860cafad0d07b9286b7bf8ed9efa683120a412a388"
},
"downloads": -1,
"filename": "hvae_backbone-0.1.126-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6ed91d9855ff9927fd339180f045236a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 43074,
"upload_time": "2024-02-05T12:19:47",
"upload_time_iso_8601": "2024-02-05T12:19:47.727871Z",
"url": "https://files.pythonhosted.org/packages/2f/73/6cafcbbeda700bb9b079ab88091f0574a2c1b14ea401e9a2122fb9385787/hvae_backbone-0.1.126-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "3327acf659493dc6ab1df92c82decf649d928794886b8c22b55d924172a092ae",
"md5": "b7009ab439d485538cba273c6463b3f8",
"sha256": "e7691dac295eb4aaaeb0d41fe461af145bac31e0aae070549cd7b77bdccdffa4"
},
"downloads": -1,
"filename": "hvae_backbone-0.1.126.tar.gz",
"has_sig": false,
"md5_digest": "b7009ab439d485538cba273c6463b3f8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 34510,
"upload_time": "2024-02-05T12:19:53",
"upload_time_iso_8601": "2024-02-05T12:19:53.148788Z",
"url": "https://files.pythonhosted.org/packages/33/27/acf659493dc6ab1df92c82decf649d928794886b8c22b55d924172a092ae/hvae_backbone-0.1.126.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-05 12:19:53",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "lacykaltgr",
"github_project": "hvae-backbone",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "hvae-backbone"
}
JSON
