Dl4J? Chainer? Dynet? Give me a break. There's tons out there now. https://twitter.com/xamat/status/913654270280339456 …
-
This Tweet is unavailable.
-
Replying to @xamat @agibsonccc
Caffe itself is legacy, and Caffe2 has no traction. "Dead" is too strong a qualifier, this is a gradually declining ecosystem.
1 reply 0 retweets 5 likes -
The biggest mystery in deep learning these days is why PyTorch is getting more traction than the original Chainer. Branding & marketing?...
6 replies 2 retweets 12 likes -
I don't think that's it. Many switched from chainer to pytorch
2 replies 0 retweets 4 likes -
What's the difference though?
2 replies 0 retweets 1 like -
I'm not an expert in chainer enough to know. Wish I had time to dig deep in every framework, but then I wouldn't be so deep...
2 replies 0 retweets 5 likes -
Replying to @jeremyphoward @fchollet and
Anyhoo, I definitely agree with
@agibsonccc that more competition in this space is a good thing. We all have a long way to go2 replies 0 retweets 7 likes -
Replying to @jeremyphoward @fchollet and
isnt something like http://tvmlang.org the future ?write in your fav pseudo framework, then get eventually optimised to the same thing?
2 replies 0 retweets 0 likes -
Replying to @harvey_slash @jeremyphoward and
At this time, Keras is the only framework that compiles to multiple platforms (TF, Theano, CNTK, MXNet). But maybe this will become a trend
2 replies 0 retweets 10 likes -
Replying to @fchollet @jeremyphoward and
I hope it does.I think it will be esp great if ML can be easily ported on web browser.Will unlock better creativity options for client devs.
1 reply 0 retweets 0 likes
You can already easily port Keras models to iPhone, Android, and the browser. We're getting there fast
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.