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
bac4e0d4
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
bac4e0d4
编写于
6月 22, 2016
作者:
A
A. Unique TensorFlower
提交者:
TensorFlower Gardener
6月 22, 2016
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix doc for _DNNLinearCombinedBaseEstimator.
Change: 125575345
上级
45aa96d0
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
16 addition
and
17 deletion
+16
-17
tensorflow/contrib/learn/python/learn/estimators/dnn_linear_combined.py
...trib/learn/python/learn/estimators/dnn_linear_combined.py
+16
-17
未找到文件。
tensorflow/contrib/learn/python/learn/estimators/dnn_linear_combined.py
浏览文件 @
bac4e0d4
...
@@ -80,7 +80,6 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
...
@@ -80,7 +80,6 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
Args:
Args:
model_dir: Directory to save model parameters, graph and etc.
model_dir: Directory to save model parameters, graph and etc.
n_classes: number of target classes. Default is binary classification.
weight_column_name: A string defining feature column name representing
weight_column_name: A string defining feature column name representing
weights. It is used to down weight or boost examples during training. It
weights. It is used to down weight or boost examples during training. It
will be multiplied by the loss of the example.
will be multiplied by the loss of the example.
...
@@ -92,10 +91,10 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
...
@@ -92,10 +91,10 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
dnn_feature_columns: An iterable containing all the feature columns used
dnn_feature_columns: An iterable containing all the feature columns used
by deep part of the model. All items in the set should be instances of
by deep part of the model. All items in the set should be instances of
classes derived from `FeatureColumn`.
classes derived from `FeatureColumn`.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
the deep part of the model. If `None`, will use an Adagrad optimizer.
the deep part of the model. If `None`, will use an Adagrad optimizer.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_activation_fn: Activation function applied to each layer. If `None`,
dnn_activation_fn: Activation function applied to each layer. If `None`,
will use `tf.nn.relu`.
will use `tf.nn.relu`.
dnn_dropout: When not None, the probability we will drop out
dnn_dropout: When not None, the probability we will drop out
...
@@ -108,9 +107,9 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
...
@@ -108,9 +107,9 @@ class _DNNLinearCombinedBaseEstimator(estimator.BaseEstimator):
residual after centered bias.
residual after centered bias.
config: RunConfig object to configure the runtime settings.
config: RunConfig object to configure the runtime settings.
Raises:
Raises:
ValueError: If both linear_feature_columns and dnn_features_columns are
ValueError: If both linear_feature_columns and dnn_features_columns are
empty at the same time.
empty at the same time.
"""
"""
super
(
_DNNLinearCombinedBaseEstimator
,
self
).
__init__
(
model_dir
=
model_dir
,
super
(
_DNNLinearCombinedBaseEstimator
,
self
).
__init__
(
model_dir
=
model_dir
,
config
=
config
)
config
=
config
)
...
@@ -485,10 +484,10 @@ class DNNLinearCombinedClassifier(_DNNLinearCombinedBaseEstimator):
...
@@ -485,10 +484,10 @@ class DNNLinearCombinedClassifier(_DNNLinearCombinedBaseEstimator):
dnn_feature_columns: An iterable containing all the feature columns used
dnn_feature_columns: An iterable containing all the feature columns used
by deep part of the model. All items in the set must be instances of
by deep part of the model. All items in the set must be instances of
classes derived from `FeatureColumn`.
classes derived from `FeatureColumn`.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
the deep part of the model. If `None`, will use an Adagrad optimizer.
the deep part of the model. If `None`, will use an Adagrad optimizer.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_activation_fn: Activation function applied to each layer. If `None`,
dnn_activation_fn: Activation function applied to each layer. If `None`,
will use `tf.nn.relu`.
will use `tf.nn.relu`.
dnn_dropout: When not None, the probability we will drop out
dnn_dropout: When not None, the probability we will drop out
...
@@ -501,10 +500,10 @@ class DNNLinearCombinedClassifier(_DNNLinearCombinedBaseEstimator):
...
@@ -501,10 +500,10 @@ class DNNLinearCombinedClassifier(_DNNLinearCombinedBaseEstimator):
residual after centered bias.
residual after centered bias.
config: RunConfig object to configure the runtime settings.
config: RunConfig object to configure the runtime settings.
Raises:
Raises:
ValueError: If both linear_feature_columns and dnn_features_columns are
ValueError: If both linear_feature_columns and dnn_features_columns are
empty at the same time.
empty at the same time.
ValueError: If both n_classes < 2.
ValueError: If both n_classes < 2.
"""
"""
if
n_classes
<
2
:
if
n_classes
<
2
:
...
@@ -732,10 +731,10 @@ class DNNLinearCombinedRegressor(_DNNLinearCombinedBaseEstimator):
...
@@ -732,10 +731,10 @@ class DNNLinearCombinedRegressor(_DNNLinearCombinedBaseEstimator):
dnn_feature_columns: An iterable containing all the feature columns used
dnn_feature_columns: An iterable containing all the feature columns used
by deep part of the model. All items in the set must be instances of
by deep part of the model. All items in the set must be instances of
classes derived from `FeatureColumn`.
classes derived from `FeatureColumn`.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
the deep part of the model. If `None`, will use an Adagrad optimizer.
the deep part of the model. If `None`, will use an Adagrad optimizer.
dnn_hidden_units: List of hidden units per layer. All layers are fully
connected.
dnn_activation_fn: Activation function applied to each layer. If None,
dnn_activation_fn: Activation function applied to each layer. If None,
will use `tf.nn.relu`.
will use `tf.nn.relu`.
dnn_dropout: When not None, the probability we will drop out
dnn_dropout: When not None, the probability we will drop out
...
@@ -748,9 +747,9 @@ class DNNLinearCombinedRegressor(_DNNLinearCombinedBaseEstimator):
...
@@ -748,9 +747,9 @@ class DNNLinearCombinedRegressor(_DNNLinearCombinedBaseEstimator):
residual after centered bias.
residual after centered bias.
config: RunConfig object to configure the runtime settings.
config: RunConfig object to configure the runtime settings.
Raises:
Raises:
ValueError: If both linear_feature_columns and dnn_features_columns are
ValueError: If both linear_feature_columns and dnn_features_columns are
empty at the same time.
empty at the same time.
"""
"""
super
(
DNNLinearCombinedRegressor
,
self
).
__init__
(
super
(
DNNLinearCombinedRegressor
,
self
).
__init__
(
model_dir
=
model_dir
,
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