The formula of adaptive_std in your code may be wrong

llouislu / tensorflow-dain

A TensorFlow 2 Implemention of Deep Adaptive Input Normalization for Time Series Using Keras API

3 stars 1 forks source link

Open josephlau opened 3 years ago

josephlau commented 3 years ago

fn = lambda elem: K.switch(K.less_equal(elem, 1.0), K.ones_like(elem), elem) adaptive_std = K.map_fn(fn, adaptive_std)

In author's code is adaptive_std[adaptive_std <= self.eps] = 1

which self.eps = 1e-8

josephlau commented 3 years ago

Btw, change to tf.where() from map_fn results much faster training time

llouislu commented 3 years ago

@josephlau Can you please test my updated code https://github.com/llouislu/tensorflow-dain/tree/bugfix-1 if you're still interested? as I don't have access to data and environment to test dain at the moment.