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
qq_38905368
tensorflow
提交
6ae10aab
T
tensorflow
项目概览
qq_38905368
/
tensorflow
与 Fork 源项目一致
从无法访问的项目Fork
通知
5
Star
0
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
T
tensorflow
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
体验新版 GitCode,发现更多精彩内容 >>
提交
6ae10aab
编写于
6月 20, 2016
作者:
A
A. Unique TensorFlower
提交者:
TensorFlower Gardener
6月 20, 2016
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Add class descriptions for DNNClassifier and DNNRegressor, and minor
comment/reformat in examples. Change: 125374843
上级
84f4e8f3
变更
1
显示空白变更内容
内联
并排
Showing
1 changed file
with
17 addition
and
11 deletion
+17
-11
tensorflow/contrib/learn/python/learn/estimators/dnn.py
tensorflow/contrib/learn/python/learn/estimators/dnn.py
+17
-11
未找到文件。
tensorflow/contrib/learn/python/learn/estimators/dnn.py
浏览文件 @
6ae10aab
...
...
@@ -76,7 +76,7 @@ class DNNClassifier(dnn_linear_combined.DNNLinearCombinedClassifier):
whose `value` is a `SparseTensor`.
- if `column` is a `RealValuedColumn, a feature with `key=column.name`
whose `value` is a `Tensor`.
- if `feauture_columns` is
None
, then `input` must contains only real
- if `feauture_columns` is
`None`
, then `input` must contains only real
valued `Tensor`.
"""
...
...
@@ -96,7 +96,7 @@ class DNNClassifier(dnn_linear_combined.DNNLinearCombinedClassifier):
Args:
hidden_units: List of hidden units per layer. All layers are fully
connected. Ex.
[64, 32]
means first layer has 64 nodes and second one
connected. Ex.
`[64, 32]`
means first layer has 64 nodes and second one
has 32.
feature_columns: An iterable containing all the feature columns used by
the model. All items in the set should be instances of classes derived
...
...
@@ -111,7 +111,7 @@ class DNNClassifier(dnn_linear_combined.DNNLinearCombinedClassifier):
`None`, will use an Adagrad optimizer.
activation_fn: Activation function applied to each layer. If `None`, will
use `tf.nn.relu`.
dropout: When not
None
, the probability we will drop out a given
dropout: When not
`None`
, the probability we will drop out a given
coordinate.
gradient_clip_norm: A float > 0. If provided, gradients are
clipped to their global norm with this clipping ratio. See
...
...
@@ -119,7 +119,10 @@ class DNNClassifier(dnn_linear_combined.DNNLinearCombinedClassifier):
enable_centered_bias: A bool. If True, estimator will learn a centered
bias variable for each class. Rest of the model structure learns the
residual after centered bias.
config: RunConfig object to configure the runtime settings.
config: `RunConfig` object to configure the runtime settings.
Returns:
A `DNNClassifier` estimator.
"""
super
(
DNNClassifier
,
self
).
__init__
(
model_dir
=
model_dir
,
...
...
@@ -199,7 +202,7 @@ class DNNRegressor(dnn_linear_combined.DNNLinearCombinedRegressor):
whose `value` is a `SparseTensor`.
- if `column` is a `RealValuedColumn, a feature with `key=column.name`
whose `value` is a `Tensor`.
- if `feauture_columns` is
None
, then `input` must contains only real
- if `feauture_columns` is
`None`
, then `input` must contains only real
valued `Tensor`.
"""
...
...
@@ -218,8 +221,8 @@ class DNNRegressor(dnn_linear_combined.DNNLinearCombinedRegressor):
Args:
hidden_units: List of hidden units per layer. All layers are fully
connected. Ex.
[64, 32] means first layer has 64 nodes and second
one
has 32.
connected. Ex.
`[64, 32]` means first layer has 64 nodes and second one
has 32.
feature_columns: An iterable containing all the feature columns used by
the model. All items in the set should be instances of classes derived
from `FeatureColumn`.
...
...
@@ -231,15 +234,18 @@ class DNNRegressor(dnn_linear_combined.DNNLinearCombinedRegressor):
`None`, will use an Adagrad optimizer.
activation_fn: Activation function applied to each layer. If `None`, will
use `tf.nn.relu`.
dropout: When not
None
, the probability we will drop out a given
dropout: When not
`None`
, the probability we will drop out a given
coordinate.
gradient_clip_norm: A
float
> 0. If provided, gradients are clipped
gradient_clip_norm: A
`float`
> 0. If provided, gradients are clipped
to their global norm with this clipping ratio. See
tf.clip_by_global_norm
for more details.
`tf.clip_by_global_norm`
for more details.
enable_centered_bias: A bool. If True, estimator will learn a centered
bias variable for each class. Rest of the model structure learns the
residual after centered bias.
config: RunConfig object to configure the runtime settings.
config: `RunConfig` object to configure the runtime settings.
Returns:
A `DNNRegressor` estimator.
"""
super
(
DNNRegressor
,
self
).
__init__
(
model_dir
=
model_dir
,
...
...
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