versions/0.11.0/tutorials/r/charRnnModel.html

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta content="IE=edge" http-equiv="X-UA-Compatible"/> <meta content="width=device-width, initial-scale=1" name="viewport"/> <meta content="Char RNN Example" property="og:title"> <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image"> <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url"> <meta content="Char RNN Example" property="og:description"/> <title>Char RNN Example — mxnet documentation</title> <link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/> <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/> <link href="../../_static/basic.css" rel="stylesheet" type="text/css"> <link href="../../_static/pygments.css" rel="stylesheet" type="text/css"> <link href="../../_static/mxnet.css" rel="stylesheet" type="text/css"/> <script type="text/javascript"> var DOCUMENTATION_OPTIONS = { URL_ROOT: '../../', VERSION: '', COLLAPSE_INDEX: false, FILE_SUFFIX: '.html', HAS_SOURCE: true, SOURCELINK_SUFFIX: '.txt' }; </script> <script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script> <script src="../../_static/underscore.js" type="text/javascript"></script> <script src="../../_static/searchtools_custom.js" type="text/javascript"></script> <script src="../../_static/doctools.js" type="text/javascript"></script> <script src="../../_static/selectlang.js" type="text/javascript"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> <script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/0.11.0/searchindex.js"); Search.init();}); </script>          <link href="../../genindex.html" rel="index" title="Index"> <link href="../../search.html" rel="search" title="Search"/> <link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/> </link></link></link></meta></meta></meta></head> <body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document"> <div class="content-block"><div class="navbar navbar-fixed-top"> <div class="container" id="navContainer"> <div class="innder" id="header-inner"> <h1 id="logo-wrap"> <a href="../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a> </h1> <nav class="nav-bar" id="main-nav"> <a class="main-nav-link" href="/versions/0.11.0/get_started/install.html">Install</a> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/0.11.0/tutorials/gluon/gluon.html">About</a></li> <li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li> <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> </ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/0.11.0/api/python/index.html">Python</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/c++/index.html">C++</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/julia/index.html">Julia</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/perl/index.html">Perl</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/r/index.html">R</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/scala/index.html">Scala</a></li> </ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs"> <li><a class="main-nav-link" href="/versions/0.11.0/how_to/faq.html">FAQ</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/tutorials/index.html">Tutorials</a> <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v0.11.0/example">Examples</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/architecture/index.html">Architecture</a></li> <li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/model_zoo/index.html">Model Zoo</a></li> <li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li> </li></ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community"> <li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li> <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v0.11.0">Github</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/community/contribute.html">Contribute</a></li> </ul> <a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">0.11.0</a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7.0/">1.7.0</a></li><li><a href=/versions/1.6.0/>1.6.0</a></li><li><a href=/versions/1.5.0/>1.5.0</a></li><li><a href=/versions/1.4.1/>1.4.1</a></li><li><a href=/versions/1.3.1/>1.3.1</a></li><li><a href=/versions/1.2.1/>1.2.1</a></li><li><a href=/versions/1.1.0/>1.1.0</a></li><li><a href=/versions/1.0.0/>1.0.0</a></li><li><a href=/versions/0.12.1/>0.12.1</a></li><li><a href=/versions/0.11.0/>0.11.0</a></li></ul></nav> <script> function getRootPath(){ return "../../" } </script> <div class="burgerIcon dropdown"> <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a> <ul class="dropdown-menu" id="burgerMenu"> <li><a href="/versions/0.11.0/get_started/install.html">Install</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/tutorials/index.html">Tutorials</a></li> <li class="dropdown-submenu dropdown"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/0.11.0/tutorials/gluon/gluon.html">About</a></li> <li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li> <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> </ul> </li> <li class="dropdown-submenu"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a> <ul class="dropdown-menu"> <li><a class="main-nav-link" href="/versions/0.11.0/api/python/index.html">Python</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/c++/index.html">C++</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/julia/index.html">Julia</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/perl/index.html">Perl</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/r/index.html">R</a></li> <li><a class="main-nav-link" href="/versions/0.11.0/api/scala/index.html">Scala</a></li> </ul> </li> <li class="dropdown-submenu"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a> <ul class="dropdown-menu"> <li><a href="/versions/0.11.0/how_to/faq.html" tabindex="-1">FAQ</a></li> <li><a href="/versions/0.11.0/tutorials/index.html" tabindex="-1">Tutorials</a></li> <li><a href="https://github.com/apache/incubator-mxnet/tree/v0.11.0/example" tabindex="-1">Examples</a></li> <li><a href="/versions/0.11.0/architecture/index.html" tabindex="-1">Architecture</a></li> <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li> <li><a href="/versions/0.11.0/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li> <li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li> </ul> </li> <li class="dropdown-submenu dropdown"> <a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a> <ul class="dropdown-menu"> <li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li> <li><a href="https://github.com/apache/incubator-mxnet/tree/v0.11.0" tabindex="-1">Github</a></li> <li><a href="/versions/0.11.0/community/contribute.html" tabindex="-1">Contribute</a></li> </ul> </li> <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">0.11.0</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6.0/>1.6.0</a></li><li><a tabindex="-1" href=/versions/1.5.0/>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/>0.11.0</a></li></ul></li></ul> </div> <div class="plusIcon dropdown"> <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"></a> <ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul> </div> <div id="search-input-wrap"> <form action="../../search.html" autocomplete="off" class="" method="get" role="search"> <div class="form-group inner-addon left-addon"> <input class="form-control" name="q" placeholder="Search" type="text"/> </div> <input name="check_keywords" type="hidden" value="yes"> <input name="area" type="hidden" value="default"/> </input></form> <div id="search-preview"></div> </div> <div id="searchIcon"> </div>            </div> </div> </div> <script type="text/javascript"> $('body').css('background', 'white'); </script> <div class="container"> <div class="row"> <div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation"> <div class="sphinxsidebarwrapper"> <ul> <li class="toctree-l1"><a class="reference internal" href="../../api/python/index.html">Python Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/r/index.html">R Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/julia/index.html">Julia Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/c++/index.html">C++ Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/scala/index.html">Scala Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/perl/index.html">Perl Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../how_to/index.html">HowTo Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../architecture/index.html">System Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../index.html">Tutorials</a></li> </ul> </div> </div> <div class="content"> <div class="page-tracker"></div> <div class="section" id="char-rnn-example"> <h1>Char RNN Example<a class="headerlink" href="#char-rnn-example" title="Permalink to this headline">¶</a></h1> This tutorial shows how to use an LSTM model to build a char-level language model, and generate text from it. For demonstration purposes, we use a Shakespearean text. You can find the data on <a class="reference external" href="https://github.com/dmlc/web-data/tree/master/mxnet/tinyshakespeare">GitHub</a>. <div class="section" id="load-the-data"> <h2>Load the Data<a class="headerlink" href="#load-the-data" title="Permalink to this headline">¶</a></h2> Load in the data and preprocess it: <div class="highlight-r"><div class="highlight"><pre> require(mxnet) </pre></div> </div> <div class="highlight-default"><div class="highlight"><pre> ## Loading required package: mxnet </pre></div> </div> <div class="highlight-default"><div class="highlight"><pre> ## Loading required package: methods </pre></div> </div> Set the basic network parameters: <div class="highlight-r"><div class="highlight"><pre> batch.size = 32 seq.len = 32 num.hidden = 16 num.embed = 16 num.lstm.layer = 1 num.round = 1 learning.rate= 0.1 wd=0.00001 clip_gradient=1 update.period = 1 </pre></div> </div> Download the data: <div class="highlight-r"><div class="highlight"><pre> download.data <- function(data_dir) { dir.create(data_dir, showWarnings = FALSE) if (!file.exists(paste0(data_dir,'input.txt'))) { download.file(url='https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/tinyshakespeare/input.txt', destfile=paste0(data_dir,'input.txt'), method='wget') } } </pre></div> </div> Make a dictionary from the text: <div class="highlight-r"><div class="highlight"><pre> make.dict <- function(text, max.vocab=10000) { text <- strsplit(text, '') dic <- list() idx <- 1 for (c in text[[1]]) { if (!(c %in% names(dic))) { dic[[c]] <- idx idx <- idx + 1 } } if (length(dic) == max.vocab - 1) dic[["UNKNOWN"]] <- idx cat(paste0("Total unique char: ", length(dic), "\n")) return (dic) } </pre></div> </div> Transfer the text into a data feature: <div class="highlight-r"><div class="highlight"><pre> make.data <- function(file.path, seq.len=32, max.vocab=10000, dic=NULL) { fi <- file(file.path, "r") text <- paste(readLines(fi), collapse="\n") close(fi) if (is.null(dic)) dic <- make.dict(text, max.vocab) lookup.table <- list() for (c in names(dic)) { idx <- dic[[c]] lookup.table[[idx]] <- c } char.lst <- strsplit(text, '')[[1]] num.seq <- as.integer(length(char.lst) / seq.len) char.lst <- char.lst[1:(num.seq * seq.len)] data <- array(0, dim=c(seq.len, num.seq)) idx <- 1 for (i in 1:num.seq) { for (j in 1:seq.len) { if (char.lst[idx] %in% names(dic)) data[j, i] <- dic[[ char.lst[idx] ]]-1 else { data[j, i] <- dic[["UNKNOWN"]]-1 } idx <- idx + 1 } } return (list(data=data, dic=dic, lookup.table=lookup.table)) } </pre></div> </div> Move the tail text: <div class="highlight-r"><div class="highlight"><pre> drop.tail <- function(X, batch.size) { shape <- dim(X) nstep <- as.integer(shape[2] / batch.size) return (X[, 1:(nstep * batch.size)]) } </pre></div> </div> Get the label of X: <div class="highlight-r"><div class="highlight"><pre> get.label <- function(X) { label <- array(0, dim=dim(X)) d <- dim(X)[1] w <- dim(X)[2] for (i in 0:(w-1)) { for (j in 1:d) { label[i*d+j] <- X[(i*d+j)%%(w*d)+1] } } return (label) } </pre></div> </div> Get the training data and evaluation data: <div class="highlight-r"><div class="highlight"><pre> download.data("./data/") ret <- make.data("./data/input.txt", seq.len=seq.len) </pre></div> </div> <div class="highlight-default"><div class="highlight"><pre> ## Total unique char: 65 </pre></div> </div> <div class="highlight-r"><div class="highlight"><pre> X <- ret$data dic <- ret$dic lookup.table <- ret$lookup.table vocab <- length(dic) shape <- dim(X) train.val.fraction <- 0.9 size <- shape[2] X.train.data <- X[, 1:as.integer(size * train.val.fraction)] X.val.data <- X[, -(1:as.integer(size * train.val.fraction))] X.train.data <- drop.tail(X.train.data, batch.size) X.val.data <- drop.tail(X.val.data, batch.size) X.train.label <- get.label(X.train.data) X.val.label <- get.label(X.val.data) X.train <- list(data=X.train.data, label=X.train.label) X.val <- list(data=X.val.data, label=X.val.label) </pre></div> </div> </div> <div class="section" id="train-the-model"> <h2>Train the Model<a class="headerlink" href="#train-the-model" title="Permalink to this headline">¶</a></h2> In <code class="docutils literal">mxnet</code>, we have a function called <code class="docutils literal">mx.lstm</code> so that users can build a general LSTM model: <div class="highlight-r"><div class="highlight"><pre> model <- mx.lstm(X.train, X.val, ctx=mx.cpu(), num.round=num.round, update.period=update.period, num.lstm.layer=num.lstm.layer, seq.len=seq.len, num.hidden=num.hidden, num.embed=num.embed, num.label=vocab, batch.size=batch.size, input.size=vocab, initializer=mx.init.uniform(0.1), learning.rate=learning.rate, wd=wd, clip_gradient=clip_gradient) </pre></div> </div> <div class="highlight-default"><div class="highlight"><pre> ## Epoch [31] Train: NLL=3.53787130224343, Perp=34.3936275728271 ## Epoch [62] Train: NLL=3.43087958036949, Perp=30.903813186055 ## Epoch [93] Train: NLL=3.39771238228587, Perp=29.8956319855751 ## Epoch [124] Train: NLL=3.37581711716687, Perp=29.2481732041015 ## Epoch [155] Train: NLL=3.34523331338447, Perp=28.3671933405139 ## Epoch [186] Train: NLL=3.30756356274787, Perp=27.31848454823 ## Epoch [217] Train: NLL=3.25642968403829, Perp=25.9566978956055 ## Epoch [248] Train: NLL=3.19825967486207, Perp=24.4898727477925 ## Epoch [279] Train: NLL=3.14013971549828, Perp=23.1070950525017 ## Epoch [310] Train: NLL=3.08747601837462, Perp=21.9216781782189 ## Epoch [341] Train: NLL=3.04015595674863, Perp=20.9085038031042 ## Epoch [372] Train: NLL=2.99839339255659, Perp=20.0532932584534 ## Epoch [403] Train: NLL=2.95940091012609, Perp=19.2864139984503 ## Epoch [434] Train: NLL=2.92603311380224, Perp=18.6534872738302 ## Epoch [465] Train: NLL=2.89482756896395, Perp=18.0803835531869 ## Epoch [496] Train: NLL=2.86668230478397, Perp=17.5786009078994 ## Epoch [527] Train: NLL=2.84089368534943, Perp=17.1310684830416 ## Epoch [558] Train: NLL=2.81725862932279, Perp=16.7309220880514 ## Epoch [589] Train: NLL=2.79518870141492, Perp=16.3657166956952 ## Epoch [620] Train: NLL=2.77445683225304, Perp=16.0299176962855 ## Epoch [651] Train: NLL=2.75490970113174, Perp=15.719621374694 ## Epoch [682] Train: NLL=2.73697900634351, Perp=15.4402696117257 ## Epoch [713] Train: NLL=2.72059739336781, Perp=15.1893935780915 ## Epoch [744] Train: NLL=2.70462837571585, Perp=14.948760335793 ## Epoch [775] Train: NLL=2.68909904683828, Perp=14.7184093476224 ## Epoch [806] Train: NLL=2.67460054451836, Perp=14.5065539595711 ## Epoch [837] Train: NLL=2.66078997776751, Perp=14.3075873113043 ## Epoch [868] Train: NLL=2.6476781639279, Perp=14.1212134100373 ## Epoch [899] Train: NLL=2.63529039846876, Perp=13.9473621677371 ## Epoch [930] Train: NLL=2.62367693518974, Perp=13.7863219168709 ## Epoch [961] Train: NLL=2.61238282674384, Perp=13.6314936713501 ## Iter [1] Train: Time: 10301.6818172932 sec, NLL=2.60536539345356, Perp=13.5361704272949 ## Iter [1] Val: NLL=2.26093848746227, Perp=9.59208699731232 </pre></div> </div> </div> <div class="section" id="build-inference-from-the-model"> <h2>Build Inference from the Model<a class="headerlink" href="#build-inference-from-the-model" title="Permalink to this headline">¶</a></h2> Use the helper function for random sample: <div class="highlight-r"><div class="highlight"><pre> cdf <- function(weights) { total <- sum(weights) result <- c() cumsum <- 0 for (w in weights) { cumsum <- cumsum+w result <- c(result, cumsum / total) } return (result) } search.val <- function(cdf, x) { l <- 1 r <- length(cdf) while (l <= r) { m <- as.integer((l+r)/2) if (cdf[m] < x) { l <- m+1 } else { r <- m-1 } } return (l) } choice <- function(weights) { cdf.vals <- cdf(as.array(weights)) x <- runif(1) idx <- search.val(cdf.vals, x) return (idx) } </pre></div> </div> Use random output or fixed output by choosing the greatest probability: <div class="highlight-r"><div class="highlight"><pre> make.output <- function(prob, sample=FALSE) { if (!sample) { idx <- which.max(as.array(prob)) } else { idx <- choice(prob) } return (idx) } </pre></div> </div> In <code class="docutils literal">mxnet</code>, we have a function called <code class="docutils literal">mx.lstm.inference</code> so that users can build an inference from an LSTM model, and then use the <code class="docutils literal">mx.lstm.forward</code> function to get forward output from the inference. Build an inference from the model: <div class="highlight-r"><div class="highlight"><pre> infer.model <- mx.lstm.inference(num.lstm.layer=num.lstm.layer, input.size=vocab, num.hidden=num.hidden, num.embed=num.embed, num.label=vocab, arg.params=model$arg.params, ctx=mx.cpu()) </pre></div> </div> Generate a sequence of 75 characters using the <code class="docutils literal">mx.lstm.forward</code> function: <div class="highlight-r"><div class="highlight"><pre> start <- 'a' seq.len <- 75 random.sample <- TRUE last.id <- dic[[start]] out <- "a" for (i in (1:(seq.len-1))) { input <- c(last.id-1) ret <- mx.lstm.forward(infer.model, input, FALSE) infer.model <- ret$model prob <- ret$prob last.id <- make.output(prob, random.sample) out <- paste0(out, lookup.table[[last.id]]) } cat (paste0(out, "\n")) </pre></div> </div> The result: <div class="highlight-default"><div class="highlight"><pre> ah not a drobl greens Settled asing lately sistering sounted to their hight </pre></div> </div> </div> <div class="section" id="create-other-rnn-models"> <h2>Create Other RNN Models<a class="headerlink" href="#create-other-rnn-models" title="Permalink to this headline">¶</a></h2> In <code class="docutils literal">mxnet</code>, other RNN models, like custom RNN and GRU, are also provided: <ul class="simple"> <li>For a custom RNN model, you can replace <code class="docutils literal">mx.lstm</code> with <code class="docutils literal">mx.rnn</code> to train an RNN model. You can replace <code class="docutils literal">mx.lstm.inference</code> and <code class="docutils literal">mx.lstm.forward</code> with <code class="docutils literal">mx.rnn.inference</code> and <code class="docutils literal">mx.rnn.forward</code> to build inference from an RNN model and get the forward result from the inference model.</li> <li>For a GRU model, you can replace <code class="docutils literal">mx.lstm</code> with <code class="docutils literal">mx.gru</code> to train a GRU model. You can replace <code class="docutils literal">mx.lstm.inference</code> and <code class="docutils literal">mx.lstm.forward</code> with <code class="docutils literal">mx.gru.inference</code> and <code class="docutils literal">mx.gru.forward</code> to build inference from a GRU model and get the forward result from the inference model.</li> </ul> </div> <div class="section" id="next-steps"> <h2>Next Steps<a class="headerlink" href="#next-steps" title="Permalink to this headline">¶</a></h2> <div class="toctree-wrapper compound"> <ul> <li class="toctree-l1"><a class="reference external" href="/versions/0.11.0/tutorials/index.html">MXNet tutorials index</a></li> </ul> </div> </div> </div> </div> </div> <div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation"> <div class="sphinxsidebarwrapper"> <h3><a href="../../index.html">Table Of Contents</a></h3> <ul> <li><a class="reference internal" href="#">Char RNN Example</a><ul> <li><a class="reference internal" href="#load-the-data">Load the Data</a></li> <li><a class="reference internal" href="#train-the-model">Train the Model</a></li> <li><a class="reference internal" href="#build-inference-from-the-model">Build Inference from the Model</a></li> <li><a class="reference internal" href="#create-other-rnn-models">Create Other RNN Models</a></li> <li><a class="reference internal" href="#next-steps">Next Steps</a></li> </ul> </li> </ul> </div> </div> </div><div class="footer"> <div class="section-disclaimer"> <div class="container"> <div> <img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/> Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. "Copyright © 2017-2018, The Apache Software Foundation Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation." </div> </div> </div> </div>  </div> <script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script> <script src="../../_static/js/sidebar.js" type="text/javascript"></script> <script src="../../_static/js/search.js" type="text/javascript"></script> <script src="../../_static/js/navbar.js" type="text/javascript"></script> <script src="../../_static/js/clipboard.min.js" type="text/javascript"></script> <script src="../../_static/js/copycode.js" type="text/javascript"></script> <script src="../../_static/js/page.js" type="text/javascript"></script> <script src="../../_static/js/docversion.js" type="text/javascript"></script> <script type="text/javascript"> $('body').ready(function () { $('body').css('visibility', 'visible'); }); </script> </body> </html>

versions/0.11.0/tutorials/r/charRnnModel.html (515 lines of code) (raw):