-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Source commit: 6511674 Nikola version: 7.8.15
- Loading branch information
Unknown
committed
Nov 26, 2020
1 parent
b3cb030
commit 79e9882
Showing
20 changed files
with
617 additions
and
51 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"github": [6, "/categories/github/", {"posts": [{"date": "07/04/2020", "isodate": "2020-07-04T18:06:00+12:00", "title": "New WekaDeeplearning4j Release - Pretrained Models, Feature Extraction Update, and more", "url": "/posts/2020-07-04-wekaDeeplearning4j-1.6.0/"}, {"date": "09/23/2019", "isodate": "2019-09-23T13:21:00+12:00", "title": "Weka Debian packages", "url": "/posts/2019-09-23-weka-debian-packages/"}, {"date": "02/16/2019", "isodate": "2019-02-16T13:48:00+12:00", "title": "Micro averages in multi-class classification", "url": "/posts/2019-02-16-micro_average/"}, {"date": "01/30/2019", "isodate": "2019-01-30T11:10:00+12:00", "title": "Oversampling and Undersampling", "url": "/posts/2019-01-30-sampling/"}, {"date": "10/08/2018", "isodate": "2018-10-08T16:02:00+12:00", "title": "Making a Weka classifier", "url": "/posts/2018-10-08-making-a-weka-classifier/"}, {"date": "05/30/2018", "isodate": "2018-05-30T22:02:00+12:00", "title": "Weka is now on Github", "url": "/posts/2018-05-30-weka-on-github/"}]}], "gui": [1, "/categories/gui/", {"posts": [{"date": "03/01/2019", "isodate": "2019-03-01T11:10:00+12:00", "title": "Bookmarks support", "url": "/posts/2019-03-01-bookmarks/"}]}], "kotlin": [1, "/categories/kotlin/", {"posts": [{"date": "06/22/2018", "isodate": "2018-06-22T08:00:00+12:00", "title": "Weka-Kt: Kotlin Extensions for Weka", "url": "/posts/2018-06-22-wekakotlin/"}]}], "scripting": [2, "/categories/scripting/", {"posts": [{"date": "04/02/2019", "isodate": "2019-04-02T13:44:00+13:00", "title": "Jupyter notebooks (on Windows)", "url": "/posts/2019-04-02-jupyter-windows/"}, {"date": "03/29/2019", "isodate": "2019-03-29T14:04:00+13:00", "title": "Jupyter notebooks", "url": "/posts/2019-03-29-jupyter/"}]}]} | ||
{"github": [7, "/categories/github/", {"posts": [{"date": "11/26/2020", "isodate": "2020-11-26T18:06:00+12:00", "title": "New WekaDeeplearning4j Release - CNN explorer, saliency maps, progress manager, and model summaries", "url": "/posts/2020-11-26-wekaDeeplearning4j-1.7.0/"}, {"date": "07/04/2020", "isodate": "2020-07-04T18:06:00+12:00", "title": "New WekaDeeplearning4j Release - Pretrained Models, Feature Extraction Update, and more", "url": "/posts/2020-07-04-wekaDeeplearning4j-1.6.0/"}, {"date": "09/23/2019", "isodate": "2019-09-23T13:21:00+12:00", "title": "Weka Debian packages", "url": "/posts/2019-09-23-weka-debian-packages/"}, {"date": "02/16/2019", "isodate": "2019-02-16T13:48:00+12:00", "title": "Micro averages in multi-class classification", "url": "/posts/2019-02-16-micro_average/"}, {"date": "01/30/2019", "isodate": "2019-01-30T11:10:00+12:00", "title": "Oversampling and Undersampling", "url": "/posts/2019-01-30-sampling/"}, {"date": "10/08/2018", "isodate": "2018-10-08T16:02:00+12:00", "title": "Making a Weka classifier", "url": "/posts/2018-10-08-making-a-weka-classifier/"}, {"date": "05/30/2018", "isodate": "2018-05-30T22:02:00+12:00", "title": "Weka is now on Github", "url": "/posts/2018-05-30-weka-on-github/"}]}], "gui": [1, "/categories/gui/", {"posts": [{"date": "03/01/2019", "isodate": "2019-03-01T11:10:00+12:00", "title": "Bookmarks support", "url": "/posts/2019-03-01-bookmarks/"}]}], "kotlin": [1, "/categories/kotlin/", {"posts": [{"date": "06/22/2018", "isodate": "2018-06-22T08:00:00+12:00", "title": "Weka-Kt: Kotlin Extensions for Weka", "url": "/posts/2018-06-22-wekakotlin/"}]}], "scripting": [2, "/categories/scripting/", {"posts": [{"date": "04/02/2019", "isodate": "2019-04-02T13:44:00+13:00", "title": "Jupyter notebooks (on Windows)", "url": "/posts/2019-04-02-jupyter-windows/"}, {"date": "03/29/2019", "isodate": "2019-03-29T14:04:00+13:00", "title": "Jupyter notebooks", "url": "/posts/2019-03-29-jupyter/"}]}]} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,32 @@ | ||
<?xml version="1.0" encoding="utf-8"?> | ||
<?xml-stylesheet type="text/xsl" href="../assets/xml/rss.xsl" media="all"?><rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/"><channel><title>WEKA Blog (Posts by Rhys Compton)</title><link>https://waikato.github.io/weka-blog/</link><description></description><atom:link rel="self" href="https://waikato.github.io/weka-blog/authors/rhys-compton.xml" type="application/rss+xml"></atom:link><language>en</language><lastBuildDate>Thu, 26 Nov 2020 06:29:11 GMT</lastBuildDate><generator>Nikola (getnikola.com)</generator><docs>http://blogs.law.harvard.edu/tech/rss</docs><item><title>New WekaDeeplearning4j Release - CNN explorer, saliency maps, progress manager, and model summaries</title><link>https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/</link><dc:creator>Rhys Compton</dc:creator><description><div><p>A new version of WekaDeeplearning4j, version 1.7.0, is available!</p> | ||
<!-- TEASER_EN --> | ||
<p>![Dl4jCNNExplorer and Saliency map generation](../../images/GUI.jpg)</p> | ||
<p>### Dl4j Inference Panel &amp; Dl4jCNNExplorer | ||
One major addition in <strong>WekaDeeplearning4j</strong> v1.7.0 is the new <strong>Dl4jCNNExplorer</strong> and the | ||
associated GUI <strong>Dl4j Inference Panel</strong>. This brings real-time inference to the WEKA universe, | ||
allowing you to quickly run an image classification CNN model on an image without having to | ||
load an entire <cite>.arff</cite> file.</p> | ||
<p>The <strong>Dl4jCNNExplorer</strong> supports both a custom-trained <cite>Dl4jMlpClassifier</cite> and a model from | ||
the Model Zoo, so it can be used to verify your model's prediction capabilities | ||
or simply play around with pretrained models and explore what state-of-the-art | ||
architectures may work best for your domain.</p> | ||
<p>Check out the [usage example](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/">https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/</a>) | ||
to see how easy it is to get started.</p> | ||
<p>### Saliency Map Generation with ScoreCAM | ||
Another exciting new feature is the implementation of <strong>ScoreCAM</strong>, a saliency map generation technique. | ||
This can be accessed through the <cite>Dl4jCNNExplorer</cite>, allowing you to not only perform prediction on an image, | ||
but look at <em>what</em> in the image your model was using for prediction.</p> | ||
<p>This can be invoked from the command-line, although the best user experience is to be had from the GUI using the | ||
<strong>Saliency Map Viewer</strong>, which allows you to quickly customize the ScoreCAM target classes.</p> | ||
<p>Check out the [usage example](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/#example-4-saliency-map-generation">https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/#example-4-saliency-map-generation</a>) | ||
to see what new insights can be brought to your workflow.</p> | ||
<p>### Progress Manager</p> | ||
<p>![Progress Manager](../../images/ProgressManager.png)</p> | ||
<p>We've created a simple---but effective---progress bar and added this to the long-running tasks | ||
(model training, feature extraction, etc.). This provides a graphical indicator of progress and remaining | ||
ETA for the current job so will make WEKA more usable for large jobs.</p> | ||
<p>### Model Summaries</p> | ||
<p>We've also added [model summaries](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/user-guide/model-zoo/#model-summaries">https://deeplearning.cms.waikato.ac.nz/user-guide/model-zoo/#model-summaries</a>) | ||
to the documentation, which specify the different models and their layers. This can be useful for designing | ||
your own architectures or with the <cite>Dl4jMlpFilter</cite>, when using intermediary layers for feature extraction.</p></div></description><category>github</category><guid>https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/</guid><pubDate>Thu, 26 Nov 2020 06:06:00 GMT</pubDate></item></channel></rss> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,88 @@ | ||
<!DOCTYPE html> | ||
<html prefix="og: http://ogp.me/ns# article: http://ogp.me/ns/article# " lang="en"> | ||
<head> | ||
<meta charset="utf-8"> | ||
<meta name="viewport" content="width=device-width, initial-scale=1"> | ||
<title>Posts by Rhys Compton | WEKA Blog</title> | ||
<link href="../../assets/css/all-nocdn.css" rel="stylesheet" type="text/css"> | ||
<meta name="theme-color" content="#5670d4"> | ||
<meta name="generator" content="Nikola (getnikola.com)"> | ||
<link rel="alternate" type="application/rss+xml" title="RSS for author Rhys Compton (en)" href="../rhys-compton.xml"> | ||
<link rel="canonical" href="https://waikato.github.io/weka-blog/authors/rhys-compton/"> | ||
<!--[if lt IE 9]><script src="../../assets/js/html5.js"></script><![endif]--><link rel="alternate" type="application/rss+xml" title="RSS for author Rhys Compton (en)" href="../rhys-compton.xml"> | ||
</head> | ||
<body> | ||
<a href="#content" class="sr-only sr-only-focusable">Skip to main content</a> | ||
|
||
<!-- Menubar --> | ||
|
||
<nav class="navbar navbar-inverse navbar-static-top"><div class="container"> | ||
<!-- This keeps the margins nice --> | ||
<div class="navbar-header"> | ||
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-navbar" aria-controls="bs-navbar" aria-expanded="false"> | ||
<span class="sr-only">Toggle navigation</span> | ||
<span class="icon-bar"></span> | ||
<span class="icon-bar"></span> | ||
<span class="icon-bar"></span> | ||
</button> | ||
<a class="navbar-brand" href="https://waikato.github.io/weka-blog/"> | ||
|
||
<span id="blog-title">WEKA Blog</span> | ||
</a> | ||
</div> | ||
<!-- /.navbar-header --> | ||
<div class="collapse navbar-collapse" id="bs-navbar" role="navigation" aria-expanded="false"> | ||
<ul class="nav navbar-nav"> | ||
<li> | ||
<a href="../../archive.html">Archive</a> | ||
</li> | ||
<li> | ||
<a href="../../categories/">Tags</a> | ||
</li> | ||
<li> | ||
<a href="../../rss.xml">RSS feed</a> | ||
|
||
|
||
</li> | ||
</ul> | ||
<ul class="nav navbar-nav navbar-right"></ul> | ||
</div> | ||
<!-- /.navbar-collapse --> | ||
</div> | ||
<!-- /.container --> | ||
</nav><!-- End of Menubar --><div class="container" id="content" role="main"> | ||
<div class="body-content"> | ||
<!--Body content--> | ||
<div class="row"> | ||
|
||
|
||
<article class="authorpage"><header><h1>Posts by Rhys Compton</h1> | ||
<div class="metadata"> | ||
|
||
<p class="feedlink"> | ||
<a href="../rhys-compton.xml" type="application/rss+xml">RSS feed</a> | ||
</p> | ||
|
||
</div> | ||
</header><ul class="postlist"> | ||
<li> | ||
<time class="listdate" datetime="2020-11-26T18:06:00+12:00" title="2020-11-26 18:06">2020-11-26 18:06</time><a href="../../posts/2020-11-26-wekaDeeplearning4j-1.7.0/" class="listtitle">New WekaDeeplearning4j Release - CNN explorer, saliency maps, progress manager, and model summaries</a> | ||
</li> | ||
</ul></article> | ||
</div> | ||
<!--End of body content--> | ||
|
||
<footer id="footer"> | ||
Contents © 2020 <a href="mailto:[email protected]">The WEKA Team</a> - Powered by <a href="https://getnikola.com" rel="nofollow">Nikola</a> | ||
|
||
</footer> | ||
</div> | ||
</div> | ||
|
||
|
||
<script src="../../assets/js/all-nocdn.js"></script><script>$('a.image-reference:not(.islink) img:not(.islink)').parent().colorbox({rel:"gal",maxWidth:"100%",maxHeight:"100%",scalePhotos:true});</script><!-- fancy dates --><script> | ||
moment.locale("en"); | ||
fancydates(0, "YYYY-MM-DD HH:mm"); | ||
</script><!-- end fancy dates --> | ||
</body> | ||
</html> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,33 @@ | ||
<?xml version="1.0" encoding="utf-8"?> | ||
<?xml-stylesheet type="text/xsl" href="../assets/xml/rss.xsl" media="all"?><rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/"><channel><title>WEKA Blog (Posts about packages)</title><link>https://waikato.github.io/weka-blog/</link><description></description><atom:link href="https://waikato.github.io/weka-blog/categories/cat_packages.xml" rel="self" type="application/rss+xml"></atom:link><language>en</language><lastBuildDate>Sat, 04 Jul 2020 08:37:15 GMT</lastBuildDate><generator>Nikola (getnikola.com)</generator><docs>http://blogs.law.harvard.edu/tech/rss</docs><item><title>New WekaDeeplearning4j Release - Pretrained Models, Feature Extraction Update, and more</title><link>https://waikato.github.io/weka-blog/posts/2020-07-04-wekaDeeplearning4j-1.6.0/</link><dc:creator>Eibe Frank</dc:creator><description><div><p>A new version of WekaDeeplearning4j, version 1.6.0, has just been released and brings with it a bunch of exciting new features.</p> | ||
<?xml-stylesheet type="text/xsl" href="../assets/xml/rss.xsl" media="all"?><rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/"><channel><title>WEKA Blog (Posts about packages)</title><link>https://waikato.github.io/weka-blog/</link><description></description><atom:link rel="self" href="https://waikato.github.io/weka-blog/categories/cat_packages.xml" type="application/rss+xml"></atom:link><language>en</language><lastBuildDate>Thu, 26 Nov 2020 06:29:11 GMT</lastBuildDate><generator>Nikola (getnikola.com)</generator><docs>http://blogs.law.harvard.edu/tech/rss</docs><item><title>New WekaDeeplearning4j Release - CNN explorer, saliency maps, progress manager, and model summaries</title><link>https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/</link><dc:creator>Rhys Compton</dc:creator><description><div><p>A new version of WekaDeeplearning4j, version 1.7.0, is available!</p> | ||
<!-- TEASER_EN --> | ||
<p>![Dl4jCNNExplorer and Saliency map generation](../../images/GUI.jpg)</p> | ||
<p>### Dl4j Inference Panel &amp; Dl4jCNNExplorer | ||
One major addition in <strong>WekaDeeplearning4j</strong> v1.7.0 is the new <strong>Dl4jCNNExplorer</strong> and the | ||
associated GUI <strong>Dl4j Inference Panel</strong>. This brings real-time inference to the WEKA universe, | ||
allowing you to quickly run an image classification CNN model on an image without having to | ||
load an entire <cite>.arff</cite> file.</p> | ||
<p>The <strong>Dl4jCNNExplorer</strong> supports both a custom-trained <cite>Dl4jMlpClassifier</cite> and a model from | ||
the Model Zoo, so it can be used to verify your model's prediction capabilities | ||
or simply play around with pretrained models and explore what state-of-the-art | ||
architectures may work best for your domain.</p> | ||
<p>Check out the [usage example](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/">https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/</a>) | ||
to see how easy it is to get started.</p> | ||
<p>### Saliency Map Generation with ScoreCAM | ||
Another exciting new feature is the implementation of <strong>ScoreCAM</strong>, a saliency map generation technique. | ||
This can be accessed through the <cite>Dl4jCNNExplorer</cite>, allowing you to not only perform prediction on an image, | ||
but look at <em>what</em> in the image your model was using for prediction.</p> | ||
<p>This can be invoked from the command-line, although the best user experience is to be had from the GUI using the | ||
<strong>Saliency Map Viewer</strong>, which allows you to quickly customize the ScoreCAM target classes.</p> | ||
<p>Check out the [usage example](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/#example-4-saliency-map-generation">https://deeplearning.cms.waikato.ac.nz/examples/dl4j-inference/#example-4-saliency-map-generation</a>) | ||
to see what new insights can be brought to your workflow.</p> | ||
<p>### Progress Manager</p> | ||
<p>![Progress Manager](../../images/ProgressManager.png)</p> | ||
<p>We've created a simple---but effective---progress bar and added this to the long-running tasks | ||
(model training, feature extraction, etc.). This provides a graphical indicator of progress and remaining | ||
ETA for the current job so will make WEKA more usable for large jobs.</p> | ||
<p>### Model Summaries</p> | ||
<p>We've also added [model summaries](<a class="reference external" href="https://deeplearning.cms.waikato.ac.nz/user-guide/model-zoo/#model-summaries">https://deeplearning.cms.waikato.ac.nz/user-guide/model-zoo/#model-summaries</a>) | ||
to the documentation, which specify the different models and their layers. This can be useful for designing | ||
your own architectures or with the <cite>Dl4jMlpFilter</cite>, when using intermediary layers for feature extraction.</p></div></description><category>github</category><guid>https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/</guid><pubDate>Thu, 26 Nov 2020 06:06:00 GMT</pubDate></item><item><title>New WekaDeeplearning4j Release - Pretrained Models, Feature Extraction Update, and more</title><link>https://waikato.github.io/weka-blog/posts/2020-07-04-wekaDeeplearning4j-1.6.0/</link><dc:creator>Eibe Frank</dc:creator><description><div><p>A new version of WekaDeeplearning4j, version 1.6.0, has just been released and brings with it a bunch of exciting new features.</p> | ||
<p><a href="https://waikato.github.io/weka-blog/posts/2020-07-04-wekaDeeplearning4j-1.6.0/">Read more…</a> (1 min remaining to read)</p></div></description><category>github</category><guid>https://waikato.github.io/weka-blog/posts/2020-07-04-wekaDeeplearning4j-1.6.0/</guid><pubDate>Sat, 04 Jul 2020 06:06:00 GMT</pubDate></item></channel></rss> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.