-
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: def3b91 Nikola version: 7.8.15
- Loading branch information
Unknown
committed
Nov 26, 2020
1 parent
79e9882
commit 48da9e0
Showing
7 changed files
with
102 additions
and
179 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,32 +1,3 @@ | ||
| <?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></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></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> | ||
| <?xml-stylesheet type="text/xsl" href="../assets/xml/rss.xsl" media="all"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><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 06:50:01 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> | ||
| <p><a href="https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/">Read more…</a> (2 min remaining to read)</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 |
|---|---|---|
| @@ -1,33 +1,4 @@ | ||
| <?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 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></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></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> | ||
| <?xml-stylesheet type="text/xsl" href="../assets/xml/rss.xsl" media="all"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><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 06:50:01 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> | ||
| <p><a href="https://waikato.github.io/weka-blog/posts/2020-11-26-wekaDeeplearning4j-1.7.0/">Read more…</a> (2 min remaining to read)</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.