{"id":22107443,"url":"https://github.com/vikktor93/convnet","last_synced_at":"2025-03-24T03:22:14.580Z","repository":{"id":265557765,"uuid":"896198598","full_name":"Vikktor93/ConvNet","owner":"Vikktor93","description":" This repository compares the performance of a Multilayer Perceptron (MLP) and a Convolutional Neural Network (CNN) in the task of binary classification of images of muffins and chihuahuas.","archived":false,"fork":false,"pushed_at":"2024-12-03T02:37:56.000Z","size":60866,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-29T09:36:55.050Z","etag":null,"topics":["cnn-classification","cnn-keras","cnn-model","data-science","machine-learning","machine-learning-algorithms","mlp-classifier"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Vikktor93.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-29T18:53:56.000Z","updated_at":"2024-12-03T02:38:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"129cf202-6820-4902-9e3c-fe22d6ec12e9","html_url":"https://github.com/Vikktor93/ConvNet","commit_stats":null,"previous_names":["vikktor93/convnet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vikktor93%2FConvNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vikktor93%2FConvNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vikktor93%2FConvNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vikktor93%2FConvNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vikktor93","download_url":"https://codeload.github.com/Vikktor93/ConvNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245201215,"owners_count":20576779,"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","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":["cnn-classification","cnn-keras","cnn-model","data-science","machine-learning","machine-learning-algorithms","mlp-classifier"],"created_at":"2024-12-01T08:17:32.536Z","updated_at":"2025-03-24T03:22:14.538Z","avatar_url":"https://github.com/Vikktor93.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"left\"\u003e\n   \u003cimg src=\"https://img.shields.io/badge/Status-En%20Desarrollo-green?style=plastic\"\u003e\n   \u003cimg src=\"https://img.shields.io/badge/Python-3776AB?style=plastic\u0026logo=python\u0026logoColor=white\"/\u003e\n   \u003cimg src=\"https://img.shields.io/badge/Jupyter-%23e58f1a.svg?style=plastic\u0026logo=Jupyter\u0026logoColor=white\"/\u003e\n\n\u003cimg src=\"./assets/banner-CNN.png\"/\u003e\n\n## Tarea 2 - Redes Convolucionales\n\nEsta tarea compara el desempeño de un Perceptrón Multicapa (MLP) y una Red Neuronal Convolucional (CNN) en la tarea de clasificación binaria de imágenes de muffins y chihuahuas. El dataset utilizado para esta tarea se encuentra en [Kaggle](https://www.kaggle.com/datasets/samuelcortinhas/muffin-vs-chihuahua-image-classification). \n\n## Descripción\n\nEl objetivo principal es explorar y evaluar diferentes arquitecturas de redes neuronales en un problema de clasificación de imágenes. Para ello, se utilizan dos modelos principales:\n\n- **Perceptrón Multicapa (MLP):** Modelo completamente conectado que trata las imágenes como un vector plano.\n- **Red Neuronal Convolucional (CNN):** Modelo que aprovecha la estructura espacial de las imágenes para extraer características.\n\nSe incluye un conjunto de datos con imágenes de muffins y chihuahuas, el cual es procesado y aumentado para mejorar el rendimiento de los modelos.\n\n## Tecnologías Utilizadas\n- Python 3.10.8\n- TensorFlow/Keras: Para el diseño y entrenamiento de las redes neuronales.\n- NumPy y Pandas: Manipulación y análisis de datos.\n- Matplotlib: Visualización de métricas y datos.\n- ImageDataGenerator: Para aumento de datos y preprocesamiento\n\n## Estructura del Proyecto\n\nLa estructura del proyecto es la siguiente:\n```\n.\n├── data/                     # Contiene las imágenes organizadas en carpetas (muffins/chihuahuas)\n│   ├── train/                # Datos de entrenamiento\n│   └── test/                 # Datos de prueba\n├── 001-ConvNet.ipynb         # Cuaderno Jupyter utilizado para el análisis, entrenamiento y para los modelos\n├── README.md                 # Descripción del proyecto\n└── .gitattributes            # Configuración de Git para el manejo de archivos y texto\n\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvikktor93%2Fconvnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvikktor93%2Fconvnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvikktor93%2Fconvnet/lists"}