0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

chainerの作法 その4

Last updated at Posted at 2018-05-03

概要

chainerの作法を調べてみた。
オプチマイザー。

使ったモデル

分類。

class MLP(Chain):
	def __init__(self, n_in, n_units, n_out):
		super(MLP, self).__init__(l1 = L.Linear(n_in, n_units), l2 = L.Linear(None, n_out))
	def __call__(self, x):
		return self.l2(F.relu(self.l1(x)))

model = L.Classifier(MLP(6, 128, 4))


optimizers.Adam()

opti_Adam.png

optimizers.SGD()

opti_SGD.png

optimizers.AdaGrad()

opti_AdaGrad.png

optimizers.AdaDelta()

opti_AdaDelta.png

optimizers.MomentumSGD()

opti_MomentumSGD.png

optimizers.RMSprop()

opti_RMSprop.png

optimizers.RMSpropGraves()

opti_RMSpropGraves.png

以上。

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?