Git Product home page Git Product logo

dnn's Introduction

DNN

pull docker image

Prerequisite

  • CUDA install
  • MeCab install
git clone https://github.com/taku910/mecab.git
cd mecab/mecab
./configure
make
make check
make install

Compile & Execution

Assume cuMat directory is in the same row.

cp test.cpp.[Type of processing] test.cpp
make
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../cuMat
./test
  • If you get an error, test.cpp:8:17: fatal error: png.h: No such file or directory
apt-get install libpng12-0
apt-get install libpng-dev
find / -name png.h
  • install boost
apt-get install libboost-all-dev
  • install utilities
apt update
apt install git
apt install net-tools
apt install net-tools
apt install vim-tiny

[Type of processing]

  • autoencoder:
  • cnn: CONVOLUTION NEURAL NETWORK
  • iris: HIERARCHICAL PERCEPTRON BY IRIS DATA SET
  • lstm.sin:sin wave reproduction with LSTM
  • mlp:stratified interceptron by MNIST
  • number:LSTM Counting
  • seq2seq:LSTM Translation Model

Download MNIST(test.cpp.mlp, for autoencoder)

http://yann.lecun.com/exdb/mnist/

train-images-idx3-ubyte.gz: training set images (9912422 bytes)

train-labels-idx1-ubyte.gz: training set labels (28881 bytes)

t10k-images-idx3-ubyte.gz: test set images (1648877 bytes)

t10k-labels-idx1-ubyte.gz:   test set labels (4542 bytes)

Download and Extract to DNN Directory

Cifar-10 Download (for test.cpp.cnn)

https://www.cs.toronto.edu/~kriz/cifar.html

CIFAR-10 binary version (suitable for C programs)

Downloaded and extracted to DNN directory with data stored under cifar-10-batches-bin directory.

Tanaka Corpus Download(for test.cpp.seq2seq)

http://www.edrdg.org/wiki/index.php/Tanaka_Corpus

complete version (UTF-8) Download and extract to the DNN directory, including examples.utf.

Extract only the necessary part of examples.utf from norm_tanaka_corpus.py and create tanaka_corpus_e.txt and tanaka_corpus_j.txt.

Randomly extract 10000 items from the data created above with sample_tanaka_corpus.py and save them in a separate file (tanaka_corpus_e_10000.txt, tanaka_corpus_j_10000.txt). Rename this to use as training data (tanaka_corpus_e_10000.txt.train, tanaka_corpus_j_10000.txt.train)

Similarly, use sample_tanaka_corpus.py again to create data for evaluation.(tanaka_corpus_e_10000.txt.test, tanaka_corpus_j_10000.txt.test)

dnn's People

Contributors

endland avatar ftakezo avatar takezo5096 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.