Posts Tagged ‘ machine learning ’

TensorFlow: another Deep Learning library?

The week starts with interesting but predictable news. There is one more player there in Deep Learning. We had Caffe, Torch, Theano and now we have TensorFlow vying for our deep learning solutions.

I have questions, for example why its called Tensor Flow? might be because they are not presenting themselves as another Deep Learning library but as a library that can represent flow of Data in a graph. Those graph nodes could be computational or just data-pushers. That makes me think of them different from other deep learning libraries, atleast from Caffe.

Let me confess, I have only used Caffe. And I have found it really easy to use, however getting around setting up specific network with different form of learning looks really difficult thing to do. Torch, I heard lets you setup your own learning mechanism, however I have never worked with it. As per recent Tombone’s small survey more people are inclined to use Caffe, might be because its easy to use.

TensorFlow looks exciting, their tutorial section is also well curated. It has shine and smoothness of the any product made by the big corporate rather than roughness we see in most of academic based products. However how much its “open source” is really an open-source (easy to change, easy to update, etc…) and how much we can play with the code rather than just use it as API is going to define where it will be used. My feeling is that TensorFlow’s API will be in use pretty quickly however whether it will be used to re-imagine existing Deep Learning Paradigm is still a question.


Can Computer Vision do that?

I was listening to one Bach as recorded for BBC Proms Bach Day ‘Passacaglia and fugue’, in the comments of youtube video there was reference to the Flute player.  I wanted to know where the video captured the Flute player so I had to walk through whole video (somewhat Binary search manner) until I found the video clip.

While searching I began wondering can recent technology solve problem of finding that part of video where it shows certain instrument is being “played”. Note the PLAYED part.

The naive way is to find the frames where e.g. Flute is being shown, then use the sound analysis to find whether in  those frames we can hear the Flute sound or not. It appears to be good solution, however the problem is finding where the Flute is being played is not easy when many other instruments are also playing. Secondly it’s not necessarily that the flute person that is being shown is actually playing flute also.

Question is Can we judge (both using the sound and not using sound) whether in given clip some instrument is being “PLAYED” or is being just shown,

Try this by looking at this video while you enjoy the amazing Bach (From 4:37)