search

flrngel / cpc-tensorflow

Tensorflow implementation of "Representation Learning with Contrastive Predictive Coding"
64 stars 14 forks source link

Batch Normalization not Dropped #3

Closed ylfzr closed 6 years ago

ylfzr commented 6 years ago

Thanks very much for this share. I noticed that the original paper said they do not use batch normalizaiton in the ResNet101 encoder, however, bn is still applied in this implementation. Will this be problematic? How will this change affects the representations extracted by the model?

flrngel commented 6 years ago

I missed batch norm during massive code changes. I'll check on this issue in 24 hour and will mention you again. Thanks!

11.08 still have no time.. wait for extra 24 hour please 😭

flrngel commented 6 years ago

I've update code which doesn't use batch normalization. Thanks!