Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
BaiXuePrincess
Paddle
提交
5e8646ab
P
Paddle
项目概览
BaiXuePrincess
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
5e8646ab
编写于
6月 17, 2018
作者:
Q
qiaolongfei
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add doc for AdagradOptimizer
上级
d2b791a0
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
28 addition
and
3 deletion
+28
-3
python/paddle/fluid/optimizer.py
python/paddle/fluid/optimizer.py
+28
-3
未找到文件。
python/paddle/fluid/optimizer.py
浏览文件 @
5e8646ab
...
@@ -282,7 +282,7 @@ class SGDOptimizer(Optimizer):
...
@@ -282,7 +282,7 @@ class SGDOptimizer(Optimizer):
Examples:
Examples:
.. code-block:: python
.. code-block:: python
sgd_optimizer =
SGDOptimizer
(learning_rate=0.2)
sgd_optimizer =
fluid.optimizer.SGD
(learning_rate=0.2)
sgd_optimizer.minimize(cost)
sgd_optimizer.minimize(cost)
"""
"""
...
@@ -338,7 +338,7 @@ class MomentumOptimizer(Optimizer):
...
@@ -338,7 +338,7 @@ class MomentumOptimizer(Optimizer):
Examples:
Examples:
.. code-block:: python
.. code-block:: python
optimizer =
MomentumOptimizer
(learning_rate=0.2, momentum=0.1)
optimizer =
fluid.optimizer.Momentum
(learning_rate=0.2, momentum=0.1)
optimizer.minimize(cost)
optimizer.minimize(cost)
"""
"""
_velocity_acc_str
=
"velocity"
_velocity_acc_str
=
"velocity"
...
@@ -383,7 +383,32 @@ class MomentumOptimizer(Optimizer):
...
@@ -383,7 +383,32 @@ class MomentumOptimizer(Optimizer):
class
AdagradOptimizer
(
Optimizer
):
class
AdagradOptimizer
(
Optimizer
):
"""Simple Adagrad optimizer with moment state
"""
**Adaptive Gradient Algorithm (Adagrad)**
The update is done as follows:
.. math::
moment\_out &= moment + grad * grad
param\_out &= param -
\\
frac{learning\_rate * grad}{\sqrt{moment\_out} + \epsilon}
The original paper(http://www.jmlr.org/papers/volume12/duchi11a/duchi11a.pdf)
does not have the epsilon attribute. It is added here in our implementation
as also proposed here: http://cs231n.github.io/neural-networks-3/#ada
for numerical stability to avoid the division by zero error.
Args:
learning_rate (float|Variable): the learning rate used to update parameters.
\
Can be a float value or a Variable with one float value as data element.
epsilon (float): a small float value for numerical stability.
Examples:
.. code-block:: python
optimizer = fluid.optimizer.Adagrad(learning_rate=0.2)
optimizer.minimize(cost)
"""
"""
_moment_acc_str
=
"moment"
_moment_acc_str
=
"moment"
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录