nnlite

Name	nnlite JSON
Version	0.0.3 JSON
	download
home_page	https://github.com/huangyh09/nnlite
Summary	Some utilities and wrappers for Neural Network Models
upload_time	2024-12-15 15:14:22
maintainer	None
docs_url	None
author	['nnlite team']
requires_python	None
license	Apache-2.0
keywords	neural network models machine learning
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # nnlite
A light toolbox with utilities and wrappers for Neural Network Models


## Install

```
# for published version
pip install -U nnlite

# or developing version
pip install -U git+https://github.com/huangyh09/nnlite
```

## Quick Usage

```python
import nnlite
from functools import partial

torch.manual_seed(0)
dev = 'cuda:0' if torch.cuda.is_available() else 'cpu'

## VAE model (one hidden layer, dim=64), loss, and optimizer
model = nnlite.models.VAE_base(1838, 32, hidden_dims=[64], device=dev)
criterion = partial(nnlite.models.Loss_VAE_Gaussian, beta=1e-3)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3, weight_decay=0.95)

## NNWrapper for model training
my_wrapper = nnlite.NNWrapper(model, criterion, optimizer, device=dev)
my_wrapper.fit(train_loader, epoch=3000, validation_loader=None, verbose=False)
my_wrapper.predict(test_loader)

plt.plot(my_wrapper.train_losses)
```


## Examples
See the [examples](./examples) folder, including
* CNN-1D: [CamoTSS-CNN-demo.ipynb](./examples/CamoTSS-CNN-demo.ipynb)
* VAE for 3K PBMC: [PBMC3K_VAE.ipynb](./examples/PBMC3K_VAE.ipynb)
* and more.

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/huangyh09/nnlite",
    "name": "nnlite",
    "maintainer": null,
    "docs_url": null,
    "requires_python": null,
    "maintainer_email": null,
    "keywords": "Neural Network Models, Machine Learning",
    "author": "['nnlite team']",
    "author_email": "yuanhua@hku.hk",
    "download_url": "https://files.pythonhosted.org/packages/69/8b/31538e5acbcacb2d1b872c1b61dff71960cc9d2a8fdacf3e714cc5634a22/nnlite-0.0.3.tar.gz",
    "platform": null,
    "description": "# nnlite\nA light toolbox with utilities and wrappers for Neural Network Models\n\n\n## Install\n\n```\n# for published version\npip install -U nnlite\n\n# or developing version\npip install -U git+https://github.com/huangyh09/nnlite\n```\n\n## Quick Usage\n\n```python\nimport nnlite\nfrom functools import partial\n\ntorch.manual_seed(0)\ndev = 'cuda:0' if torch.cuda.is_available() else 'cpu'\n\n## VAE model (one hidden layer, dim=64), loss, and optimizer\nmodel = nnlite.models.VAE_base(1838, 32, hidden_dims=[64], device=dev)\ncriterion = partial(nnlite.models.Loss_VAE_Gaussian, beta=1e-3)\noptimizer = torch.optim.Adam(model.parameters(), lr=1e-3, weight_decay=0.95)\n\n## NNWrapper for model training\nmy_wrapper = nnlite.NNWrapper(model, criterion, optimizer, device=dev)\nmy_wrapper.fit(train_loader, epoch=3000, validation_loader=None, verbose=False)\nmy_wrapper.predict(test_loader)\n\nplt.plot(my_wrapper.train_losses)\n```\n\n\n## Examples\nSee the [examples](./examples) folder, including\n* CNN-1D: [CamoTSS-CNN-demo.ipynb](./examples/CamoTSS-CNN-demo.ipynb)\n* VAE for 3K PBMC: [PBMC3K_VAE.ipynb](./examples/PBMC3K_VAE.ipynb)\n* and more.\n",
    "bugtrack_url": null,
    "license": "Apache-2.0",
    "summary": "Some utilities and wrappers for Neural Network Models",
    "version": "0.0.3",
    "project_urls": {
        "Homepage": "https://github.com/huangyh09/nnlite"
    },
    "split_keywords": [
        "neural network models",
        " machine learning"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "698b31538e5acbcacb2d1b872c1b61dff71960cc9d2a8fdacf3e714cc5634a22",
                "md5": "05fdeed94b77a0f99fdc3a2952ffe774",
                "sha256": "244b62f8af79c280c0526934ae018706de46ad00fcf3fee87bb28a320ababe85"
            },
            "downloads": -1,
            "filename": "nnlite-0.0.3.tar.gz",
            "has_sig": false,
            "md5_digest": "05fdeed94b77a0f99fdc3a2952ffe774",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 2010896,
            "upload_time": "2024-12-15T15:14:22",
            "upload_time_iso_8601": "2024-12-15T15:14:22.737976Z",
            "url": "https://files.pythonhosted.org/packages/69/8b/31538e5acbcacb2d1b872c1b61dff71960cc9d2a8fdacf3e714cc5634a22/nnlite-0.0.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-12-15 15:14:22",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "huangyh09",
    "github_project": "nnlite",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "nnlite"
}