Giter Site home page Giter Site logo

river20140407 / deeplearning Goto Github PK

View Code? Open in Web Editor NEW

This project forked from andef4/deeplearning

0.0 0.0 0.0 6.99 MB

Deep Learning sample projects with PyTorch

License: MIT License

Dockerfile 0.40% Shell 0.42% Jupyter Notebook 81.40% Python 17.78%

deeplearning's Introduction

Deep Learning example projects

This repository contains multiple projects I implemented as a preparation for my bachelors thesis on the Bern University of Applied Sciences.

All projects use PyTorch and are located in the notebooks/ subdirectory. Python dependencies are saved in requirements.txt. The docker/ directory contains a Dockerfile to build a docker container containing PyTorch, CUDA and jupyter notebook.

MNIST

An implementation of the MNIST handwritten digit classification dataset.

Music

Detect the genre of a song. Use music_prepare.ipybn to generate a dataset from a local music library, then music.ipynb to train the classifier.

Icons

Detects 2D shapes (tetris stones) in real time from a webcam. This is a multi-label classifier because it can detect multiple shapes under the webcam.

Shapes3D

This is a unfinished project. It currently downloads and extracts 3D model files (*.stl) from thingiverse. The next step would be to generate renderings from different angles of the 3D models and then use these as input for the network.

One idea for a classifier would be to give the network three images of the same model from different angles and as a second input another image from the same or from another model. Then the network has to decide if the second input shows the same image as the three sample images.

Tetris

A very early attempt to create a Tetris bot. Based on code by Kevin Chabowski https://gist.github.com/silvasur/565419/d9de6a84e7da000797ac681976442073045c74a4, adjusted to work inside a jupyter notebook. Not bot code yet.

deeplearning's People

Contributors

dependabot[bot] avatar fotcorn avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.