<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[RSS Feed]]></title><description><![CDATA[RSS Feed]]></description><link>http://direct.ecency.com</link><image><url>http://direct.ecency.com/logo512.png</url><title>RSS Feed</title><link>http://direct.ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Thu, 09 Apr 2026 14:36:49 GMT</lastBuildDate><atom:link href="http://direct.ecency.com/@ronny.rest/rss" rel="self" type="application/rss+xml"/><item><title><![CDATA[Semantic Segmentation Tutorial - 02 General Structure]]></title><description><![CDATA[General Structure The general structure that is used by most of the deep neural network models for semantic segmentation is similar to the one illustrated in the diagram below. The architecture goes through]]></description><link>http://direct.ecency.com/dtube/@ronny.rest/diqj8vxt</link><guid isPermaLink="true">http://direct.ecency.com/dtube/@ronny.rest/diqj8vxt</guid><category><![CDATA[dtube]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Tue, 19 Dec 2017 08:58:09 GMT</pubDate><enclosure url="https://images.ecency.com/p/3HaJVw3AYyXB9dvtaVFb1c5wcqCGeZkEQYbAXFaEA2iBin6aUNLjqnJvetu1XNTLVfWUGCpgECxrG1KyDQdGrP4rfxjVxCS6XkzwEVy?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Semantic Segmentation Tutorial - 01 Intro]]></title><description><![CDATA[This is the first in a series of lessons about semantic segmentation. Semantic segmentation involves understanding not just what happens to be in the scene, but also what regions of the image those things]]></description><link>http://direct.ecency.com/dtube/@ronny.rest/44b78ivb</link><guid isPermaLink="true">http://direct.ecency.com/dtube/@ronny.rest/44b78ivb</guid><category><![CDATA[dtube]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Tue, 19 Dec 2017 07:50:57 GMT</pubDate><enclosure url="https://images.ecency.com/p/6VvuHGsoU2QBxYFFLuywjgtJfwdjbpYkoiukQZZHzkRSVx7DCEGGnSS2btCodwNdZVQfVVupVg3otp7bQ86J77Boje3pPqCvevSb7KdujbMGFcVHCMQ1LTjF4C5kau?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Installing Opencv on Ubuntu (for use with python)]]></title><description><![CDATA[Summary OpenCV is a really good library to use for processing video files and real time video sources from a webcam in python. Setting it up, however (at least on ubuntu), can be a little tricky. It is]]></description><link>http://direct.ecency.com/machine-learning/@ronny.rest/installing-opencv-on-ubuntu-for-use-with-python</link><guid isPermaLink="true">http://direct.ecency.com/machine-learning/@ronny.rest/installing-opencv-on-ubuntu-for-use-with-python</guid><category><![CDATA[machine-learning]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Fri, 13 Oct 2017 06:57:24 GMT</pubDate><enclosure url="https://images.ecency.com/p/RGgukq5E6HBS5wvERDA3ZF4P2WKQy2VoZZet1QV2iFHBpYeHyJKTp7NBdc6ttGSyowRdGYP222CTKNw6AN8FcujScSEYeZHZoAJUA8zhnEwuMk5hHf8xn9RokuJ7YSa?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Avoiding headaches with tf.metrics]]></title><description><![CDATA[1. Summary This post will cover how to avoid headaches with Tensorflow's built in evaluation metrics operations such as tf.metrics.accuracy() tf.metrics.precision() tf.metrics.recall() tf.metrics.mean_iou()]]></description><link>http://direct.ecency.com/machine-learning/@ronny.rest/avoiding-headaches-with-tf-metrics</link><guid isPermaLink="true">http://direct.ecency.com/machine-learning/@ronny.rest/avoiding-headaches-with-tf-metrics</guid><category><![CDATA[machine-learning]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Fri, 13 Oct 2017 06:10:03 GMT</pubDate><enclosure url="https://images.ecency.com/p/2r8F9rTBenJR3iqPxDrevHK3vDeQGnHc8Wj8C8neiPWxWsy4Wt6cBjPczyrMMemyVEJRHKrqkkHuM6DkyCuAiyWB98rmujeQkgLn4Wa4ngLrmzYvFgiFTn2sKhEbvUXhQ?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Argument Scopes in Tensorflow]]></title><description><![CDATA[Intro Tensorflow has a very useful feature called an argument scope. Argument scopes allow you to specify default values for tensorflow layer functions. This, in turn, allows you to write tensorflow code]]></description><link>http://direct.ecency.com/machine-learning/@ronny.rest/argument-scopes-in-tensorflow</link><guid isPermaLink="true">http://direct.ecency.com/machine-learning/@ronny.rest/argument-scopes-in-tensorflow</guid><category><![CDATA[machine-learning]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Fri, 13 Oct 2017 05:10:45 GMT</pubDate><enclosure url="https://images.ecency.com/p/2r8F9rTBenJR3iqPxDrevHK3vDeQGnHc8Wj8C8neiPWxWsy4Wt6cBjPczyrMMemyVEJRHKrqkkHuM6DkyCuAiyWB98rmujeQkgLn4Wa4ngLrmzYvFgiFTn2sKhEbvUXhQ?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Transfer Learning in Tensroflow for a New Classsification Task]]></title><description><![CDATA[Description This blog post will go through the steps needed to perform transfer learning using the Inception V3 architecture in python using Tensorflow. There are actually several types of transfer learning,]]></description><link>http://direct.ecency.com/machine-learning/@ronny.rest/transfer-learning-in-tensroflow-for-a-new-classsification-task</link><guid isPermaLink="true">http://direct.ecency.com/machine-learning/@ronny.rest/transfer-learning-in-tensroflow-for-a-new-classsification-task</guid><category><![CDATA[machine-learning]]></category><dc:creator><![CDATA[ronny.rest]]></dc:creator><pubDate>Fri, 13 Oct 2017 04:54:30 GMT</pubDate><enclosure url="https://images.ecency.com/p/2r8F9rTBenJR3iqPxDrevHK3vDeQGnHc8Wj8C8neiPWxWsy4Wt6cBjPczyrMMemyVEJRHKrqkkHuM6DkyCuAiyWB98rmujeQkgLn4Wa4ngLrmzYvFgiFTn2sKhEbvUXhQ?format=match&amp;mode=fit" length="0" type="false"/></item></channel></rss>