KerasのAutoencoderの挙動がおかしいので、やっぱ国産か？と思い、chainer試すも謎のZeroDivError。ただのdeep learningライブラリオタクみたいになってきた。やっぱ、最初のPylearn2か？
-
@fchollet history['loss']の値がまったく小さくならず、ずーと同じに。いまは、普通に多層パーセプトロン使ってます。まあ、とくにAutoencoderじゃなくてもいいかなと思って。(English is better?)
@tsjshg The Keras AE does work, so the issue is not with Keras. You can try posting your code on the Keras mailing list for more help.
-
-
@fchollet I encountered something wrong with same code. Anyway I'll try a little bit. Thanks for the advise, mailing list.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet Keras is the best way for deep learning!!Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.