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
兽拳
Paddle
提交
bc7b3a61
P
Paddle
项目概览
兽拳
/
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
1
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
1
Issue
1
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
bc7b3a61
编写于
4月 11, 2019
作者:
H
heqiaozhi
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix doc
test=develop
上级
5fb9bdc8
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
14 addition
and
8 deletion
+14
-8
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+14
-8
未找到文件。
python/paddle/fluid/layers/nn.py
浏览文件 @
bc7b3a61
...
...
@@ -11067,27 +11067,32 @@ def fsp_matrix(x, y):
def
continuous_value_model
(
input
,
cvm
,
use_cvm
=
True
):
"""
**continuous_value_model layers**
continuous value moded(cvm). now, it only consider show and click value in ctr project.
We assume that input is a embedding vector with cvm_feature, which shape is [N * D] (D is 2 + embedding dim)
if use_cvm is True, we will log(cvm_feature), and output shape is [N * D].
if use_cvm is False, we will remove cvm_feature from inp
p
ut, and output shape is [N * (D - 2)].
if use_cvm is False, we will remove cvm_feature from input, and output shape is [N * (D - 2)].
This layer accepts a tensor named input which is ID after embedded and lod level is 1
,
cvm is a show_click info.
This layer accepts a tensor named input which is ID after embedded and lod level is 1
, cvm is a show_click info.
Args:
input (Variable): a 2-D LodTensor with shape [N x D], where N is the
batch size, D is 2 + the embedding dim.
lod level = 1.
input (Variable): a 2-D LodTensor with shape [N x D], where N is the batch size, D is 2 + the embedding dim. lod level = 1.
cvm (Variable): a 2-D Tensor with shape [N x 2], where N is the batch size, 2 is show and click.
use_cvm (bool): use cvm or not. if use cvm, the output dim is the same as input
if don't use cvm, the output dim is input dim - 2(remove show and click).
(cvm op is a customized op, which input is a sequence had embedd_with_cvm default, so we need a op named cvm to decided whever use it or not.)
Returns:
Variable: A 2-D LodTensor with shape [N x D], if use cvm, D is equal to input dim,
if don't use cvm, D is equal to input dim - 2.
Variable: A 2-D LodTensor with shape [N x D], if use cvm, D is equal to input dim, if don't use cvm, D is equal to input dim - 2.
Examples:
.. code-block:: python
input = fluid.layers.data(name="input", shape=[-1, 1], lod_level=1, append_batch_size=False, dtype="int64")#, stop_gradient=False)
label = fluid.layers.data(name="label", shape=[-1, 1], append_batch_size=False, dtype="int64")
embed = fluid.layers.embedding(
...
...
@@ -11098,6 +11103,7 @@ def continuous_value_model(input, cvm, use_cvm=True):
show_clk = fluid.layers.cast(fluid.layers.concat([ones, label], axis=1), dtype='float32')
show_clk.stop_gradient = True
input_with_cvm = fluid.layers.continuous_value_model(embed, show_clk, True)
"""
helper
=
LayerHelper
(
'cvm'
,
**
locals
())
out
=
helper
.
create_variable
(
dtype
=
input
.
dtype
)
...
...
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