Images to Text – Toronto Deep Learning Demos

Looks amazing. The fact that its just returns the "Cannot connect to server of image2text models" makes me very sad.

So far I keep getting the error &quot;Cannot connect to server of image2text models&quot;<p>Anyone having any luck?

<a href="http://www.skunkieacres.com/images/rabbit_box.jpg" rel="nofollow">http:&#x2F;&#x2F;www.skunkieacres.com&#x2F;images&#x2F;rabbit_box.jpg</a><p>A picture of a rabbit in a wooden box =&gt; &quot;a cat looking into a bin full of apples&quot;<p>Mistaking a rabbit for a cat is not too bad. A bin is like a box, I suppose. I&#x27;m not sure where the apples came from.

Rekognition API released similar image to text API and it&#x27;s much more reliable than this. At least the demo works smooth and response fast. <a href="https://rekognition.com/demo/concept" rel="nofollow">https:&#x2F;&#x2F;rekognition.com&#x2F;demo&#x2F;concept</a>

We are using this research to help people learn languages in VR.<p>Take a look here: <a href="http://learnimmersive.com" rel="nofollow">http:&#x2F;&#x2F;learnimmersive.com</a>

Doesn&#x27;t look to be designed for a lot of traffic, be gentle.

Very cool:<p>Comment: If you click on source code right now it gives me to javascript alerts that were trying to print out JSON objects.

I&#x27;m curious to hear how much this is read as a sign of strong AI.

My brief survey suggests that their training sample did not include very much hardcore pornography.<p>&quot;a man and a girl are learning to play with a small pool&quot;, while poetic, is a stretch in this case.