CycleGAN-TensorFlow
CycleGAN-TensorFlow copied to clipboard
What is the maximum number of iterations?
I can not understand how to set the max-iterations in the code, Please help me to understand,thanks
There is no max-iterations in the code. Your must stop the training progress by hand by pressing Ctrl+C. Please check out this issue https://github.com/vanhuyz/CycleGAN-TensorFlow/issues/45.
Maybe I should have included this in README :)
learning_rate = (
tf.where(
tf.greater_equal(global_step, start_decay_step),
tf.train.polynomial_decay(starter_learning_rate, global_step-start_decay_step,
decay_steps, end_learning_rate,
power=1.0),
starter_learning_rate
)
)
According to the code above in model.py, if the global_step get around 200000, the learning rate will decay to 0, which means the model could never change right?
Yes! 👍
@taoyunuo @vanhuyz @u10116032 @IvanUkhov @decentralion Hello, how many suitable global_step?Thanks