{"id":14970744,"url":"https://github.com/imdeepmind/neuralpy","last_synced_at":"2025-08-13T22:31:02.015Z","repository":{"id":45035580,"uuid":"260889968","full_name":"imdeepmind/NeuralPy","owner":"imdeepmind","description":"NeuralPy:  A Keras like deep learning library works on top of PyTorch","archived":false,"fork":false,"pushed_at":"2024-06-10T02:20:57.000Z","size":3653,"stargazers_count":79,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-22T19:54:01.060Z","etag":null,"topics":["data-science","deep-learning","keras","library","machine-learning","neural-network","neuralpy","neuralpy-torch","python","pytorch"],"latest_commit_sha":null,"homepage":"https://neuralpy.imdeepmind.com/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/imdeepmind.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-03T11:01:37.000Z","updated_at":"2025-04-16T10:02:13.000Z","dependencies_parsed_at":"2022-09-12T17:11:13.082Z","dependency_job_id":null,"html_url":"https://github.com/imdeepmind/NeuralPy","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/imdeepmind/NeuralPy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeepmind%2FNeuralPy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeepmind%2FNeuralPy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeepmind%2FNeuralPy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeepmind%2FNeuralPy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/imdeepmind","download_url":"https://codeload.github.com/imdeepmind/NeuralPy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeepmind%2FNeuralPy/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270328953,"owners_count":24565769,"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","status":"online","status_checked_at":"2025-08-13T02:00:09.904Z","response_time":66,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["data-science","deep-learning","keras","library","machine-learning","neural-network","neuralpy","neuralpy-torch","python","pytorch"],"created_at":"2024-09-24T13:44:04.820Z","updated_at":"2025-08-13T22:31:01.616Z","avatar_url":"https://github.com/imdeepmind.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"https://user-images.githubusercontent.com/34741145/81591141-99752900-93d9-11ea-9ef6-cc2c68daaa19.png\" alt=\"Logo of NeuralPy\" /\u003e\n \u003cbr /\u003e\n A Keras like deep learning library works on top of PyTorch\n\u003c/p\u003e\n\n![NeuralPy Build Check](https://github.com/imdeepmind/NeuralPy/workflows/NeuralPy%20Build%20Check/badge.svg)\n![Maitained](https://img.shields.io/badge/Maitained%3F-Yes-brightgreen)\n![PyPI - Downloads](https://img.shields.io/pypi/dw/neuralpy-torch?style=flat)\n![PyPI](https://img.shields.io/pypi/v/neuralpy-torch?style=flat)\n![GitHub closed pull requests](https://img.shields.io/github/issues-pr-closed/imdeepmind/NeuralPy?style=flat)\n![GitHub issues](https://img.shields.io/github/issues/imdeepmind/NeuralPy?style=flat)\n![GitHub](https://img.shields.io/github/license/imdeepmind/NeuralPy?style=flat)\n\n## Table of contents:\n- [Table of contents:](#table-of-contents)\n- [Introduction](#introduction)\n- [PyTorch](#pytorch)\n- [Install](#install)\n- [Dependencies](#dependencies)\n- [Get Started](#get-started)\n  - [Importing the dependencies](#importing-the-dependencies)\n  - [Making some random data](#making-some-random-data)\n  - [Making the model](#making-the-model)\n  - [Training the model](#training-the-model)\n  - [Predicting using the trained model](#predicting-using-the-trained-model)\n- [Documentation](#documentation)\n- [Examples](#examples)\n- [Blogs and Tutorials](#blogs-and-tutorials)\n- [Support](#support)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Introduction\nNeuralPy is a High-Level [Keras](https://keras.io/) like deep learning library that works on top of [PyTorch](https://pytorch.org) written in pure Python. NeuralPy can be used to develop state-of-the-art deep learning models in a few lines of code. It provides a Keras like simple yet powerful interface to build and train models. \n\nHere are some highlights of NeuralPy\n - Provides an easy interface that is suitable for fast prototyping, learning, and research\n - Can run on both CPU and GPU\n - Works on top of PyTorch\n - Cross-Compatible with PyTorch models\n\n## PyTorch\nPyTorch is an open-source machine learning framework that accelerates the path from research prototyping to production deployment developed by Facebook runs on both CPU and GPU.\n\nAccording to Wikipedia, \n\u003e PyTorch is an open-source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook's AI Research lab (FAIR). It is free and open-source software released under the Modified BSD license.\n\nNeuralPy is a high-level library that works on top of PyTorch. As it works on top of PyTorch, NerualPy supports both CPU and GPU and can perform numerical operations very efficiently.\n\nIf you want to learn more about PyTorch, then please check the [PyTorch documentation](https://pytorch.org/).\n\n## Install\nTo install NeuralPy, open terminal window type the following command:\n```\npip install neuralpy-torch\n```\nIf you have multiple versions of it, then you might need to use pip3.\n```\npip3 install neuralpy-torch\n//or\npython3 -m pip install neuralpy-torch\n```\n\u003e NeuralPy requires Pytorch and Numpy, first install those\n\nCheck the documentation for Installation related information\n\n## Dependencies\nThe only dependencies of NeuralPy are Pytorch (used as backend) and Numpy.\n\n## Get Started\nLet's create a linear regression model in 100 seconds.\n\n### Importing the dependencies\n```python\nimport numpy as np\n\nfrom neuralpy.models import Sequential\nfrom neuralpy.layers.linear import Dense\nfrom neuralpy.optimizer import Adam\nfrom neuralpy.loss_functions import MSELoss\n```\n\n### Making some random data\n```python\n# Random seed for numpy\nnp.random.seed(1969)\n\n# Generating the data\nX_train = np.random.rand(100, 1) * 10\ny_train = X_train + 5 *np.random.rand(100, 1)\n\nX_validation = np.random.rand(100, 1) * 10\ny_validation = X_validation + 5 * np.random.rand(100, 1)\n\nX_test = np.random.rand(10, 1) * 10\ny_test = X_test + 5 * np.random.rand(10, 1)\n```\n\n### Making the model\n```python\n# Making the model\nmodel = Sequential()\nmodel.add(Dense(n_nodes=1, n_inputs=1, bias=True, name=\"Input Layer\"))\n\n# Building the model\nmodel.build()\n\n# Compiling the model\nmodel.compile(optimizer=Adam(), loss_function=MSELoss())\n\n# Printing model summary\nmodel.summary()\n```\n\n### Training the model\n```python\nmodel.fit(train_data=(X_train, y_train), validation_data=(X_validation, y_validation), epochs=300, batch_size=4)\n```\n\n### Predicting using the trained model\n```python\nmodel.predict(predict_data=X_test, batch_size=4)\n```\n\n## Documentation\nThe documentation for NeuralPy is available at [https://www.neuralpy.xyz/](https://www.neuralpy.xyz/)\n\n## Examples  \nSeveral example projects in NeuralPy are available at [https://github.com/imdeepmind/NeuralPy-Examples](https://github.com/imdeepmind/NeuralPy-Examples). Please check the above link.\n\n## Blogs and Tutorials\nFollowing are some links to official blogs and tutorials:\n  - [Introduction to NeuralPy: A Keras like deep learning library works on top of PyTorch](https://medium.com/@imdeepmind/introduction-to-neuralpy-a-keras-like-deep-learning-library-works-on-top-of-pytorch-3bbf1b887561)\n\n## Support\nIf you are facing any issues using NeuralPy, then please raise an issue on GitHub or contact with me. \n\nAlternatively, you can join the official NeuralPy discord server. Click [here](https://discord.gg/6aTTwbW) to join.\n\n## Contributing\nFeel free to contribute to this project. If you need some help to get started, then reach me or open a GitHub issue. Check the [CONTRIBUTING.MD](https://github.com/imdeepmind/NeuralPy/blob/master/CONTRIBUTING.md) file for more information and guidelines.\n\n## License\n[MIT](https://github.com/imdeepmind/NeuralPy/blob/master/LICENSE)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimdeepmind%2Fneuralpy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimdeepmind%2Fneuralpy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimdeepmind%2Fneuralpy/lists"}