# nano-keras
## Overview
### **nano-keras** is a deep learning library written in Python using [NumPy](https://numpy.org/). It's designed to handle the creation and training process of most neural network types, allowing you for quick and easy prototyping and deployment.
### The project is heavily inspired by [Keras](https://keras.io/), the most popular deep learning API in the world, as I'm trying to implement my library in simmilar style and functionality to Keras
## Key Features
### - Simplicity: Built using Python and NumPy, making it easy to read and understand each part
### - Educational: Intended as a learning tool to understand neural network components at a lower level
### - Customization: Allows for tinkering and understanding the core mechanics of neural network operations
## What you can find in nano-keras
### Layers: Dense, Dropout, Reshaping layers, Convolutional layers, Pooling layers and Recurrental Layers
### Optimizers: SGD, Adam, Adadelta, Adagrad, RMSProp, NAdam and much more
### Activation functions: Sigmoid, Tanh, ReLU, ELU, LeakyReLU, Softmax
### Loss functions: MAE, MSE, BCE, CCE, Hinge, Huber
### Callbacks: EarlyStopping, LearningRateScheduler, CSVLogger
### And much more, you can find all the implemented items in [here](https://github.com/MarcelWinterot/nano-keras/wiki/Feature-list)
## Instalation
### **nano-keras** is available on [PyPI](https://pypi.org/project/nano-keras/) so in order to download it open a terminal and paste:
```bash
pip install nano-keras
```
### You now should have succesfully installed nano-keras so to use it in your python file you only need to import it like this:
```py
import nano_keras
```
### If you have an issue message me on github or send me an email
## Documentation
### Documentation is under development and should be finished in the next few days
### You can access it [here](https://github.com/MarcelWinterot/nano-keras/wiki/Documentation)
## License
### This project is licensed under the MIT License - see the LICENSE file for details
## Special thanks
### I'd like to thank my teacher, [Mateusz Kozlowski](https://github.com/mattkozlowski/), who inspired me to start working on this project and kept me motivated to finish this
### Everyone who showed support for me in real life and on LinkedIn
### Without you this project would've never come to life
Raw data
{
"_id": null,
"home_page": "https://github.com/MarcelWinterot/nano-keras",
"name": "nano-keras",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "python,machine-learning,machine-learning-library,keras,numpy",
"author": "Marcel Winterot",
"author_email": "m.winterot1@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/30/f0/793e38c6c6fcccb9b9f8057a6826e238a0fa7b927df1f4f958ff95049844/nano-keras-1.2.1.tar.gz",
"platform": null,
"description": "# nano-keras\n\n## Overview\n\n### **nano-keras** is a deep learning library written in Python using [NumPy](https://numpy.org/). It's designed to handle the creation and training process of most neural network types, allowing you for quick and easy prototyping and deployment.\n\n### The project is heavily inspired by [Keras](https://keras.io/), the most popular deep learning API in the world, as I'm trying to implement my library in simmilar style and functionality to Keras\n\n## Key Features\n\n### - Simplicity: Built using Python and NumPy, making it easy to read and understand each part\n\n### - Educational: Intended as a learning tool to understand neural network components at a lower level\n\n### - Customization: Allows for tinkering and understanding the core mechanics of neural network operations\n\n## What you can find in nano-keras\n\n### Layers: Dense, Dropout, Reshaping layers, Convolutional layers, Pooling layers and Recurrental Layers\n\n### Optimizers: SGD, Adam, Adadelta, Adagrad, RMSProp, NAdam and much more\n\n### Activation functions: Sigmoid, Tanh, ReLU, ELU, LeakyReLU, Softmax\n\n### Loss functions: MAE, MSE, BCE, CCE, Hinge, Huber\n\n### Callbacks: EarlyStopping, LearningRateScheduler, CSVLogger\n\n### And much more, you can find all the implemented items in [here](https://github.com/MarcelWinterot/nano-keras/wiki/Feature-list)\n\n## Instalation\n\n### **nano-keras** is available on [PyPI](https://pypi.org/project/nano-keras/) so in order to download it open a terminal and paste:\n\n```bash\npip install nano-keras\n```\n\n### You now should have succesfully installed nano-keras so to use it in your python file you only need to import it like this:\n\n```py\nimport nano_keras\n```\n\n### If you have an issue message me on github or send me an email\n\n## Documentation\n\n### Documentation is under development and should be finished in the next few days\n\n### You can access it [here](https://github.com/MarcelWinterot/nano-keras/wiki/Documentation)\n\n## License\n\n### This project is licensed under the MIT License - see the LICENSE file for details\n\n## Special thanks\n\n### I'd like to thank my teacher, [Mateusz Kozlowski](https://github.com/mattkozlowski/), who inspired me to start working on this project and kept me motivated to finish this\n\n### Everyone who showed support for me in real life and on LinkedIn\n\n### Without you this project would've never come to life\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Deep learning library made with numpy in the style of Keras API",
"version": "1.2.1",
"project_urls": {
"Homepage": "https://github.com/MarcelWinterot/nano-keras"
},
"split_keywords": [
"python",
"machine-learning",
"machine-learning-library",
"keras",
"numpy"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "52f529522715ed192c12f87b35e29436894a1577b20a4912921a5e1024285c28",
"md5": "f67ee617c2339c5a8f402d1beebaa70d",
"sha256": "82d50444c54d8d3b55f2f4c6de760e0c2e2029a9ef395a71be7b543951ecbfb0"
},
"downloads": -1,
"filename": "nano_keras-1.2.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f67ee617c2339c5a8f402d1beebaa70d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 56529,
"upload_time": "2023-12-22T18:51:46",
"upload_time_iso_8601": "2023-12-22T18:51:46.682825Z",
"url": "https://files.pythonhosted.org/packages/52/f5/29522715ed192c12f87b35e29436894a1577b20a4912921a5e1024285c28/nano_keras-1.2.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "30f0793e38c6c6fcccb9b9f8057a6826e238a0fa7b927df1f4f958ff95049844",
"md5": "bc0a56db630291aa8ac4105013fcbe64",
"sha256": "ead059d113732c25fbe5143de581cf4635314a770d778095dcd6ee164d1b6217"
},
"downloads": -1,
"filename": "nano-keras-1.2.1.tar.gz",
"has_sig": false,
"md5_digest": "bc0a56db630291aa8ac4105013fcbe64",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 30847,
"upload_time": "2023-12-22T18:51:49",
"upload_time_iso_8601": "2023-12-22T18:51:49.131655Z",
"url": "https://files.pythonhosted.org/packages/30/f0/793e38c6c6fcccb9b9f8057a6826e238a0fa7b927df1f4f958ff95049844/nano-keras-1.2.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-22 18:51:49",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "MarcelWinterot",
"github_project": "nano-keras",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "nano-keras"
}
JSON
