Skip to content
GitLab
探索
登录
注册
主导航
搜索或转到…
项目
D
DAGMM
管理
动态
成员
标记
计划
议题
0
议题看板
里程碑
Wiki
代码
合并请求
0
仓库
分支
提交
标签
仓库图
比较修订版本
代码片段
构建
流水线
作业
流水线计划
产物
部署
发布
软件包库
运维
环境
Terraform 模块
监控
事件
服务台
分析
价值流分析
Contributor analytics
CI/CD 分析
仓库分析
模型实验
帮助
帮助
支持
GitLab 文档
比较 GitLab 各版本
社区论坛
为极狐GitLab 提交贡献
提交反馈
快捷键
?
支持
扫码加入微信群
1. 获取企业级DevOps解决方案
2. 免费或优惠考取极狐GitLab官方培训认证
代码片段
群组
项目
AIOps-NanKai
model
DAGMM
提交
d6d527c4
提交
d6d527c4
编辑于
6年前
作者:
Toshihiro Nakae
浏览文件
操作
下载
补丁
差异文件
remove tail spaces, Japanse comments
上级
c26b3ae9
无相关合并请求
变更
2
隐藏空白变更内容
行内
左右并排
显示
2 个更改的文件
README.md
+4
-4
4 个添加, 4 个删除
README.md
dagmm/compression_net.py
+1
-1
1 个添加, 1 个删除
dagmm/compression_net.py
有
5 个添加
和
5 个删除
README.md
+
4
−
4
浏览文件 @
d6d527c4
...
@@ -18,16 +18,16 @@ At initialize, you have to specify next 4 variables at least.
...
@@ -18,16 +18,16 @@ At initialize, you have to specify next 4 variables at least.
-
``comp_hiddens``
: list of int
-
``comp_hiddens``
: list of int
-
sizes of hidden layers of compression network
-
sizes of hidden layers of compression network
-
For example, if the sizes are
``[n1, n2]``
,
-
For example, if the sizes are
``[n1, n2]``
,
structure of compression network is:
structure of compression network is:
``input_size -> n1 -> n2 -> n1 -> input_sizes``
``input_size -> n1 -> n2 -> n1 -> input_sizes``
-
``comp_activation``
: function
-
``comp_activation``
: function
-
activation function of compression network
-
activation function of compression network
-
``est_hiddens``
: list of int
-
``est_hiddens``
: list of int
-
sizes of hidden layers of estimation network.
-
sizes of hidden layers of estimation network.
-
The last element of this list is assigned as n_comp.
-
The last element of this list is assigned as n_comp.
-
For example, if the sizes are
``[n1, n2]``
,
-
For example, if the sizes are
``[n1, n2]``
,
structure of estimation network is:
structure of estimation network is:
``input_size -> n1 -> n2 (= n_comp)``
``input_size -> n1 -> n2 (= n_comp)``
-
``est_activation``
: function
-
``est_activation``
: function
-
activation function of estimation network
-
activation function of estimation network
...
...
This diff is collapsed.
Click to expand it.
dagmm/compression_net.py
+
1
−
1
浏览文件 @
d6d527c4
...
@@ -72,7 +72,7 @@ class CompressionNet:
...
@@ -72,7 +72,7 @@ class CompressionNet:
# Based on the original paper, features of reconstraction error
# Based on the original paper, features of reconstraction error
# are composed of these loss functions:
# are composed of these loss functions:
# 1. loss_E : relative Euclidean distance
# 1. loss_E : relative Euclidean distance
# 2. loss_C : cosine similarity
-> ★★★ 生の cosine か、1から引くのか?
# 2. loss_C : cosine similarity
min_val
=
1e-3
min_val
=
1e-3
loss_E
=
dist_x
/
(
norm_x
+
min_val
)
loss_E
=
dist_x
/
(
norm_x
+
min_val
)
loss_C
=
0.5
*
(
1.0
-
dot_x
/
(
norm_x
*
norm_x_dash
+
min_val
))
loss_C
=
0.5
*
(
1.0
-
dot_x
/
(
norm_x
*
norm_x_dash
+
min_val
))
...
...
This diff is collapsed.
Click to expand it.
预览
0%
请重试
或
添加新附件
.
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
保存评论
取消
想要评论请
注册
或
登录