I also saw openai ppl playing with tf. I wonder how/if caffe and torch will try to keep their usershttps://twitter.com/demishassabis/status/726079159051649024 …
-
@fchollet i was having issues with array indexes. I had to switch to th to know that. I also redifining functions within session
@edersantana when debugging complex Keras layers I find it useful to switch back and forth between backends, you get complementary error msg
-
-
@fchollet yeah i do that too hahaha keras privilege. That is why I thought a numpy/autodiff backend could be useful: debugging! -
@edersantana very interesting idea but would require np support for a bunch of complex stuff: pooling, conv, autodiff... - Show replies
New conversation -
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.