wehub-resource-sync
75 lines
2.7 KiB
HTML
75 lines
2.7 KiB
HTML
<html>
|
|
<head>
|
|
<title>ConvNetJS demo: Classify toy 2D data</title>
|
|
<link href='http://fonts.googleapis.com/css?family=Cabin' rel='stylesheet' type='text/css'>
|
|
<link rel="stylesheet" href="css/style.css">
|
|
|
|
<script>
|
|
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
|
|
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
|
|
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
|
|
})(window,document,'script','//www.google-analytics.com/analytics.js','ga');
|
|
|
|
ga('create', 'UA-3698471-21', 'stanford.edu');
|
|
ga('send', 'pageview');
|
|
|
|
</script>
|
|
|
|
<script src="js/jquery-1.8.3.min.js"></script>
|
|
<script src="js/npgmain.js"></script>
|
|
<script src="../build/convnet.js"></script>
|
|
<script src="js/regression.js"></script>
|
|
|
|
<style type="text/css">
|
|
canvas {
|
|
border: 1px solid #555;
|
|
margin-top: 10px;
|
|
}
|
|
#wrap {
|
|
width: 800px;
|
|
margin-right: auto;
|
|
margin-left: auto;
|
|
margin-bottom: 200px;
|
|
}
|
|
</style>
|
|
|
|
</head>
|
|
|
|
<body onLoad="NPGinit(10);">
|
|
|
|
<div id="wrap">
|
|
<h1><a href="http://cs.stanford.edu/people/karpathy/convnetjs">ConvnetJS</a> demo: toy 1d regression</h1>
|
|
|
|
<p>The simulation below is a 1-dimensional regression where a neural network is trained to regress to y coordinates for every given point x through an L2 loss. That is, the minimized cost function computes the squared difference between the predicted y-coordinate and the "correct" y coordinate. Every 10th of a second, all points are fed to the network multiple times through the trainer class to train the network.</p>
|
|
|
|
<p>The simulation below will eval() whatever you have in the text area and reload. Feel free to explore and use ConvNetJS to instantiate your own network!</p>
|
|
|
|
<p>Report questions/bugs/suggestions to <a href="https://twitter.com/karpathy">@karpathy</a>.</p>
|
|
|
|
<textarea id="layerdef" style="width:100%; height:250px;">
|
|
</textarea>
|
|
<br /><br />
|
|
<input id="buttontp" type="submit" value="change network" onclick="reload();" style="width: 300px; height: 50px;"/>
|
|
|
|
<div style="float: right;">
|
|
Number of points to generate: <input type="text" name="num_points" id="num_data" value="20">
|
|
<input type="submit" value="regenerate data" style="height:50px;" onclick="regen_data();" />
|
|
</div>
|
|
|
|
<br />
|
|
<p style="color: red">Add data points by clicking!</p>
|
|
<br />
|
|
<input type="checkbox" name="draw_layer_outputs" id="layer_outs">
|
|
Also draw outputs of a layer (click layer button below) in red.
|
|
<br /><div id="layer_ixes"></div>
|
|
|
|
<canvas id="NPGcanvas" width="800" height="500">Browser not supported for Canvas. Get a real browser.</canvas>
|
|
|
|
<p>Go <a href="http://cs.stanford.edu/people/karpathy/convnetjs/">back to ConvNetJS</a></p>
|
|
|
|
</div>
|
|
|
|
</body>
|
|
</html>
|
|
|