Pellentesque nec neque ex. Aliquam at quam vitae lacus convallis pulvinar. Mauris vitae ullamcorper lacus. Cras nisi dui, faucibus non dolor quis, volutpat euismod massa. Donec et pulvinar erat.
This might be the ultimate stupid question but what exactly does it predict? What is in the image? If so, what do I do with this resulting array of floats?
There is no such thing as stupid questions, the point of this article was to show you the difference between running the prediction in normal and web assembly backends.
I suggest you look at the mobile net demo on tjfs GitHub repo to see what can be done with the results, but tldr is that it gives you the probability of each object it detected
Pellentesque nec neque ex. Aliquam at quam vitae lacus convallis pulvinar. Mauris vitae ullamcorper lacus. Cras nisi dui, faucibus non dolor quis, volutpat euismod massa. Donec et pulvinar erat.
Pellentesque nec neque ex. Aliquam at quam vitae lacus convallis pulvinar. Mauris vitae ullamcorper lacus. Cras nisi dui, faucibus non dolor quis, volutpat euismod massa. Donec et pulvinar erat.
This might be the ultimate stupid question but what exactly does it predict? What is in the image? If so, what do I do with this resulting array of floats?
There is no such thing as stupid questions, the point of this article was to show you the difference between running the prediction in normal and web assembly backends.
I suggest you look at the mobile net demo on tjfs GitHub repo to see what can be done with the results, but tldr is that it gives you the probability of each object it detected
Could you elaborate on how to retrieve "piano" from this?
Look at line 87 of this file
github.com/tensorflow/tfjs-example...
Tank joo.