Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Top Deep Learning Projects

github.com

Post reply on HN
Print view View original

11–20 of 36 posts

Re: Top Deep Learning Projects

#11

Post by denzil_correa »

stephanheijl wrote: post #6
agibsonccc wrote: post #4

No metrics are perfect but I highly suggest following francois chollet (fchollet on twitter and hn, creator of keras) for his monthly updates. He does a pretty good job of showing actual activity on github: https://twitter.com/fchollet/status/753980621823750145 I point this out because drive by stars of a project are easy...but it doesn't reflect actual user activity.

This is true. Stars in this context are also more indicative of projects that are attractive to a more mainstream audience. Examples like Deep Dream and Neural style, where laymen visit the Github page and star the project because it's "cool" are prominently featured, while projects like Torch and Theano have had massively more impact on the deep learning world today.

> Stars in this context are also more indicative of projects that are attractive to a more mainstream audience.

"Popular Deep Learning GitHub Projects" would have been a more accurate title. It is mentioned in the text but the title mentions "Top" which gives a different impression than the word "Popular".

Re: Top Deep Learning Projects

#12

Post by pilooch »

nl wrote: post #7

A few comments on some of these projects: Keras is pretty much the best way to do almost anything these days. If you are starting out learning, use ConvNet JS, but after that switch to Keras. TFLearn is really nice if you are already using Scikit. There's lot of frameworks on there: TensorFlow, Caffe, CNTK (that's a lot of stars for something no one outside MS uses!) Theano, Torch etc. But I think the sleeper there i…

> Also, DeepDetect! I keep trying to find that and never can remember the name.

Ah, thanks for the reference, DD author here, the funny fact about the name is that translated to my mother tongue (French), it sounds like porn ;)

Re: Top Deep Learning Projects

#13

Post by cedricblack »

nl wrote: post #7

A few comments on some of these projects: Keras is pretty much the best way to do almost anything these days. If you are starting out learning, use ConvNet JS, but after that switch to Keras. TFLearn is really nice if you are already using Scikit. There's lot of frameworks on there: TensorFlow, Caffe, CNTK (that's a lot of stars for something no one outside MS uses!) Theano, Torch etc. But I think the sleeper there i…

I ported ConvNet JS to C# in order to really understand what's going on: https://github.com/cbovar/ConvNetSharp

Re: Top Deep Learning Projects

#14

Post by nl »

pilooch wrote: post #9
nl wrote: post #8

Earlier quoted context omitted.

It was updated on 9 August. That isn't too old.

Nop, check the stats of Caffe for instance: https://github.com/BVLC/caffe This is much older than the 9th of August.

https://github.com/aymericdamien/TopDeepLearning/graphs/comm...

It is 20/11819 = 0.16% stars off. It isn't old, just not automatically updated.

Re: Top Deep Learning Projects

#15

Post by stephanheijl »

denzil_correa wrote: post #10
nl wrote: post #7

A few comments on some of these projects: Keras is pretty much the best way to do almost anything these days. If you are starting out learning, use ConvNet JS, but after that switch to Keras. TFLearn is really nice if you are already using Scikit. There's lot of frameworks on there: TensorFlow, Caffe, CNTK (that's a lot of stars for something no one outside MS uses!) Theano, Torch etc. But I think the sleeper there i…

> Keras is pretty much the best way to do almost anything these days What makes Keras take the advantage?

Very extensible API, accessible and widely used programming language (Python), the ability to use both Theano and Tensorflow as a backend and easy to implement non-linear neural networks (where data is split and merged at will) all contribute to this. Using Keras means you will almost never need to implement some custom layer or function, whilst sacrificing very little performance-wise.

Re: Top Deep Learning Projects

#16

Post by pilooch »

nl wrote: post #14
pilooch wrote: post #9

Earlier quoted context omitted.

Nop, check the stats of Caffe for instance: https://github.com/BVLC/caffe This is much older than the 9th of August.

https://github.com/aymericdamien/TopDeepLearning/graphs/comm... It is 20/11819 = 0.16% stars off. It isn't old, just not automatically updated.

Ah, it was when it got posted to HN! Count was ~9K.

Re: Top Deep Learning Projects

#17

Post by nl »

denzil_correa wrote: post #10
nl wrote: post #7

A few comments on some of these projects: Keras is pretty much the best way to do almost anything these days. If you are starting out learning, use ConvNet JS, but after that switch to Keras. TFLearn is really nice if you are already using Scikit. There's lot of frameworks on there: TensorFlow, Caffe, CNTK (that's a lot of stars for something no one outside MS uses!) Theano, Torch etc. But I think the sleeper there i…

> Keras is pretty much the best way to do almost anything these days What makes Keras take the advantage?

It's a well designed API for using deep neural networks rather than an API for doing optimized mathematical operations.

Compare how you build some vaguely comparable models in Keras[1] and raw TensorFlow[2]. Keras uses TensorFlow (or Theano) underneath, so there is no performance penalty.

It's like in Python machine learning, most people use Scikit instead of implementing things in numpy.

[1] https://github.com/fchollet/keras/blob/master/examples/mnist...

[2] https://github.com/tensorflow/tensorflow/blob/master/tensorf...

Re: Top Deep Learning Projects

#19

Post by IshKebab »

nl wrote: post #7

A few comments on some of these projects: Keras is pretty much the best way to do almost anything these days. If you are starting out learning, use ConvNet JS, but after that switch to Keras. TFLearn is really nice if you are already using Scikit. There's lot of frameworks on there: TensorFlow, Caffe, CNTK (that's a lot of stars for something no one outside MS uses!) Theano, Torch etc. But I think the sleeper there i…

CNTK is actually pretty damn good. It just lacks a good scripting interface. They're adding one though.

The network description language (now 'BrainScript') is a far nicer way to specify networks than the approaches used by any other network. Especially for recurrent networks. In CNTK you can just say `X = FutureValue(Y)` or `X = PastValue(Y)`. It's so convoluted in TensorFlow I actually never worked out how to do it.

It also has their fancy 1-bit SGD stuff, but I doubt many people use that, and it has a more restrictive license anyway.

Re: Top Deep Learning Projects

#20

Post by denzil_correa »

nl wrote: post #17
denzil_correa wrote: post #10

Earlier quoted context omitted.

> Keras is pretty much the best way to do almost anything these days What makes Keras take the advantage?

It's a well designed API for using deep neural networks rather than an API for doing optimized mathematical operations. Compare how you build some vaguely comparable models in Keras[1] and raw TensorFlow[2]. Keras uses TensorFlow (or Theano) underneath, so there is no performance penalty. It's like in Python machine learning, most people use Scikit instead of implementing things in numpy. [1] https://github.com/fchol…

Thanks! Your example to explain the differences makes me more leaning towards Keras. It feels like Scikit for Deep Learning.
Post reply on HN