{"id":18768137,"url":"https://github.com/solomonbaez/koios","last_synced_at":"2026-04-29T20:07:23.302Z","repository":{"id":155716709,"uuid":"619916216","full_name":"solomonbaez/koios","owner":"solomonbaez","description":"Neural Network Framework, built from scratch in NumPy.","archived":false,"fork":false,"pushed_at":"2023-10-10T01:35:35.000Z","size":43,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-20T22:35:55.803Z","etag":null,"topics":["machine-learning","neural-network","neural-networks","numpy"],"latest_commit_sha":null,"homepage":"","language":"Python","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/solomonbaez.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-03-27T17:04:01.000Z","updated_at":"2023-11-08T21:18:54.000Z","dependencies_parsed_at":"2023-07-20T19:15:16.476Z","dependency_job_id":null,"html_url":"https://github.com/solomonbaez/koios","commit_stats":null,"previous_names":["solomonbaez/koios-framework","solomonbaez/koios"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/solomonbaez/koios","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solomonbaez%2Fkoios","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solomonbaez%2Fkoios/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solomonbaez%2Fkoios/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solomonbaez%2Fkoios/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/solomonbaez","download_url":"https://codeload.github.com/solomonbaez/koios/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solomonbaez%2Fkoios/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32441529,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T18:12:22.909Z","status":"ssl_error","status_checked_at":"2026-04-29T18:11:33.322Z","response_time":110,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["machine-learning","neural-network","neural-networks","numpy"],"created_at":"2024-11-07T19:11:02.779Z","updated_at":"2026-04-29T20:07:18.291Z","avatar_url":"https://github.com/solomonbaez.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Koios-Framework\nKoios is a Python Neural Network Fremework built using NumPy that allows you to create, customize, and train neural network models for image analysis. Currently, categorical and regression analysis is supported. This framework provides flexibility and ease of use for both beginners and experienced deep learning practitioners interested in building on a streamlined paradigm.\n\n## Table of Contents\n\n- [Installation](#installation)\n- [Usage](#usage)\n  - [Importing Components](#importing-components)\n  - [Initializing the Dataset](#initializing-the-dataset)\n  - [Creating and Configuring the Model](#creating-and-configuring-the-model)\n  - [Training the Model](#training-the-model)\n- [TODO](#todo)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Installation\n\nYou can install Koios by cloning the GitHub repository:\n\n```bash\ngit clone https://github.com/solomonbaez/koios-framework\n```\n\n## Usage\n### Importing Components\n\nKoios is designed to be modular, with a common Model class as the organizational center. \nTo get started, import the necessary components of the framework:\n\n```python\nfrom model import Model\nfrom layers import InputLayer, DeepLayer\nfrom activators import ReLU, Sigmoid\nfrom optimizers import OptimizerAdaM\nfrom loss import *\nfrom accuracy import *\n```\n\n### Initializing the Dataset\n\nYou can use a wide variety of test libraries to initalize datasets, in this example Keras MNIST data is utilized:\n\n```python\nfrom keras.datasets import mnist\n(X, y), (X_valid, y_valid) = mnist.load_data()\n```\n\n### Creating and Configuring the Model\n\nNext, instantiate and configure your neural network model. Here's an example:\n\n```python\n# Instantiate the model\nmodel = Model()\n\n# Add layers\nmodel.add(InputLayer(2))\nmodel.add(DeepLayer(64, activation=ReLU(), l2_w=5e-4, l2_b=5e-4))\nmodel.add(DeepLayer(1, activation=Sigmoid()))\n\n# Set loss, optimizer, and accuracy objects\nmodel.set(\n    loss=BinaryCrossEntropy(),\n    optimizer=OptimizerAdaM(decay=5e-7),\n    accuracy=BinaryAccuracy()\n)\n\nmodel.finalize()\n```\n\n### Training the Model\n\nYou can train the model with your dataset using the train method:\n\n```python\n\nmodel.train(X, y, validation=(X_test, y_test), epochs=10000, report=100)\n```\n\nThis code trains the model on your dataset for a specified number of epochs, reporting progress every 100 epochs.\n\n## TODO\n- Adjust convolutions.ConvLayer to utilize NumPy tensor operations in place of naive for loops.\n- Finalize and integrate convolutions module contents into their intended modules (e.g. ConvLayer into the layers module).\n- Create test suite.\n- Register Koios on PyPI.\n\n## Contributing\n\nContributions are welcome! If you'd like to contribute to this project, please follow these steps:\n\n1. Fork the repository on GitHub.\n2. Clone your forked repository to your local machine.\n3. Create a new branch for your feature or bug fix.\n4. Make your changes and commit them.\n5. Push your changes to your fork on GitHub.\n6. Open a pull request to the main repository.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolomonbaez%2Fkoios","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsolomonbaez%2Fkoios","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolomonbaez%2Fkoios/lists"}