What is the difference between tf.gradients and tf.train.RMSPropOptimizer (lr_rate) .compute_gradients?

Question

What's the difference between

tf.gradients

and

tf.train.RMSPropOptimizer(LR_RATE).compute_gradients

If there is a difference, let's say I want to use tf.train.RMSPropOptimizer(self.lr_rate).apply_gradients()which one is preferable?

Thank!

Answer 1

, , - , RMSPropOptimizer ( ) Optimizer, compute_gradients, tf.gradients tf.gradients , tf.gradients.

, , , tf.train.RMSPropOptimizer(..) , RMSProp - .

RMSProp: (lr) (w) .

, (Momentum, AdaGrad, RMSProp) , , , . .

, RMSProp . " "

tf.gradients(..) . tf.train.Optimizer, .