from RAdam import RAdamOptimizer
train_op = RAdamOptimizer(learning_rate=0.001, beta1=0.9, beta2=0.999, weight_decay=0.0).minimize(loss)
esillekens / radam-tensorflow Goto Github PK
View Code? Open in Web Editor NEWThis project forked from taki0112/radam-tensorflow
Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"
License: MIT License