Giter VIP home page Giter VIP logo

dio-transfer-learning-python's Introduction

Bem vindo ao projeto de Aplicação do método de Transfer Learning com Python.

Nesse projeto desafio proposto pela DIO foi realizada a aplicação do método de Transfer Learning em uma rede de Deep Learning na linguagem Python no ambiente COLAB para classificar um conjunto de imagens de cães e gatos. Todos esses estudos foram feitos seguindo a trilha do bootcamp UNIMED BH 💚 com a DIO 💪 apresentado pelo especialista Diego Renan.

Arquivos e pastas

Esse estudo foi elaborado no Google Colab e o Jupyter Notebook desenvolvido pode ser acessado no arquivo transfer_learning_Final_MDS.ipynb. Nele são descritos todos os passos adotados para resolver o problema proposto.

Aplicação do método de Transfer Learning em uma rede de Deep Learning na linguagem Python no ambiente COLAB.

Este desafio consiste em usar uma rede neural pré treinanda em um problema de identificação de cães e gatos. A rede pré-treinada foi otimizada em uma pequena parcela dos dados conhecidos (imagens de gatos e cachorros).

Esse processo consiste em pegar uma rede neural existente que já foi previamente treinada com boa performance em um grande banco de dados e usá-la como base para um novo modelo de rede neural permitindo uma melhora na acurácia do modelo. Essa estratégia tem se tornado popular nos últimos tempos.

Serviços/Recursos utilizados nesse desafio

  • Jupyter Notebook.
  • Google Colab.
  • Dataset cats_vs_dogs disponível no site da microsoft.
  • Biblioteca Keras do Python.

Autor

Moysés Dutra da Silva

linkedin LinkedIn   github Github

Licença

[MIT] https://choosealicense.com/licenses/mit

English

Welcome to the project Transfer learning with Python!

In this project proposed by DIO, We applied a method transfer learning in an neural network to classify an dataset with images of dogs an cats using Google Colab Notebook. All these studies were carried out according to the trail from the UNIMED BH 💚 bootcamp with DIO 💪 presented by Diego Renan.

Files and Folders

This study was done using Google Colab and Jupyter Notebook, and the script made can be accessed in file transfer_learning_Final_MDS.ipynb. We describe all steps did to resolve this challenge.

Using the Transfer Learning Method in Python on Google Colab enviroment.

This challenge consists in use an pre trainned neural network on a classification problem with cats and dogs images. The neural network previously trainned was optimized on an small pets dataset.

Services/resources used in this challenge

  • Jupyter Notebook.
  • Google Colab.
  • Dataset cats_vs_dogs in microsoft website.
  • Biblioteca Keras do Python.

Author

Moysés Dutra da Silva

linkedin LinkedIn   github Github

License

[MIT] https://choosealicense.com/licenses/mit

dio-transfer-learning-python's People

Contributors

moysesdutra avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.