absl.flags._exceptions.IllegalFlagValueError: flag --decay_rate=0.1: Expect argument to be a string or int, found <class 'float'>

Question

sevany opened this issue 5 years ago · 3 comments

i tried to run train.py without changing anything. do i need to use tensorflow-gpu to run train.py?

Answer 1 · 2020-04-16T13:44:54.000Z

okay solved.

Answer 2 · 2020-06-15T06:12:09.000Z

okay solved.

How to deal with？

Answer 3 · 2020-08-04T20:12:39.000Z

@liufeiwu change
tf.app.flags.DEFINE_integer('decay_rate', 0.1, '')
to
tf.app.flags.DEFINE_float('decay_rate', 0.1, '')
in main/train.py