This website works better with JavaScript.
Home
Issues
Pull Requests
Milestones
AI流水线
Repositories
Datasets
Forum
实训
竞赛
大数据
AI开发
Register
Sign In
zzy34407230
/
mindspore2022
Not watched
Unwatch
Watch all
Watch but not notify
1
Star
0
Fork
0
Code
Releases
22
Wiki
evaluate
Activity
Issues
0
Pull Requests
0
Datasets
Model
Cloudbrain
HPC
Browse Source
!31858
fix docs bugs
Merge pull request
!31858
from wanyiming/code_docs_bugs
r1.7
i-robot
Gitee
4 years ago
parent
7711af5847
ab63205216
commit
ec3831be43
No known key found for this signature in database
GPG Key ID:
173E9B9CA92EEF8F
1 changed files
with
1 additions
and
1 deletions
Split View
Diff Options
Show Stats
Download Patch File
Download Diff File
+1
-1
docs/api/api_python/nn/mindspore.nn.optim_group_dynamic_weight_decay.rst
+ 1
- 1
docs/api/api_python/nn/mindspore.nn.optim_group_dynamic_weight_decay.rst
View File
@@ -1,3 +1,3 @@
- **weight_decay** - 可选。如果键中存在"weight_decay”,则使用对应的值作为权重衰减值。如果没有,则使用优化器中配置的 `weight_decay` 作为权重衰减值。
值得注意的是,`weight_decay`可以是常量,也可以是Cell类型。Cell类型的weight decay用于实现动态weight decay算法。这和动态学习率相似。
值得注意的是,
`weight_decay`
可以是常量,也可以是Cell类型。Cell类型的weight decay用于实现动态weight decay算法。这和动态学习率相似。
用户需要自定义一个输入为global step的weight_decay_schedule。在训练的过程中,优化器会调用WeightDecaySchedule的实例来获取当前step的weight decay值。
Write
Preview
Loading…
Cancel
Save