You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Our implementation is in TensorFlow (Abadi et al. [2016]) and we use the Adam optimizer (Kingma and Ba [2014]) with its TensorFlow default parameters, including the exponentially decaying learning rate
The current capsulenet.py uses lr_decay as a callback to modify the learning rate, but there isn't any evidence that the paper follows this method. Should the lr_decay callback be removed since Adam already decays the learning rate?
(update: the TensorFlow and Keras defaults for Adam appear to be the same)
The text was updated successfully, but these errors were encountered:
@glangford As I said in README.md, I'm not sure if the paper used this learning rate decay method. I found that adopting lr_decay can lead to faster convergence. You can remove it and train for more epochs, it's your choice.
The paper says in 4:
The TensorFlow defaults for Adam are described here:
https://www.tensorflow.org/api_docs/python/tf/train/AdamOptimizer
The current capsulenet.py uses
lr_decay
as a callback to modify the learning rate, but there isn't any evidence that the paper follows this method. Should thelr_decay
callback be removed since Adam already decays the learning rate?(update: the TensorFlow and Keras defaults for Adam appear to be the same)
The text was updated successfully, but these errors were encountered: