minor point: if someone doesn't want to use pretrained models, the default is no weight reg, which is suboptimal
I've added the Inception v3 model to our model collection:https://github.com/fchollet/deep-learning-models …
-
-
-
for example, the keras resnet has no weight reg, when the FB team trained it with 0.0001 l2 reg on bias + weights.
- Show replies
New conversation -
-
-
YES
! I was just reading "Information-theoretical label embeddings for
large-scale image classification" http://arxiv.org/pdf/1607.05691v1.pdf …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.