The Good, Bad, & Ugly of TensorFlow

  • If you are deploying a model to a cloud environment, you want to know that your model can execute on the hardware available to it, without unpredictable interactions with other code that may access the same hardware.
  • For me, holding mental context for a new framework and model I’m building to solve a hard problem is already pretty taxing, so it can be really helpful to inspect a totally different representation of a model; the TensorBoard graph visualization is great for this.
  • For example, the Udacity tutorials and the RNN tutorial using Penn TreeBank data to build a language model are very illustrative, thanks to their simplicity.

Read the full article, click here.

@rasbt: “The Good, Bad, & Ugly of TensorFlow – survey of 6 months rapid evolution (+ tips/hacks & code to fix the ugly stuff)”

//php wp_head(); ?>

!function(){var||[];if(!analytics.initialize)if(analytics.invoked)window.console&&console.error&&console.error(“Segment snippet included twice.”);else{analytics.invoked=!0;analytics.methods=[“trackSubmit”,”trackClick”,”trackLink”,”trackForm”,”pageview”,”identify”,”group”,”track”,”ready”,”alias”,”page”,”once”,”off”,”on”];analytics.factory=function(t){return function(){var;e.unshift(t);analytics.push(e);return analytics}};for(var t=0;t li > a.nav-link {
-webkit-transition: all 200ms ease-out;
-moz-transition: all 200ms ease-out;
-o-transition: all 200ms ease-out;
transition: all 200ms ease-out;
font-size: 1em;
margin: 15px 8px;
padding: 0px;
width: 106px;
border: 1px solid white;
border-radius: 3px;
display: inline-block;
color: #A655CB;
border-color: #A655CB;

.nav.navbar-nav.navbar-right > li > a.nav-link:hover {
text-decoration: none;
color: #C39EF0;
border-color: #C39EF0;

.nav.navbar-nav > li > {
color: white;

.nav.navbar-nav > li > {
content: “”;
height: 2px;
background: white;
display: block;

#content {
background: white;

The Good, Bad, & Ugly of TensorFlow