提交 dcf8cf17 编写于 作者: Y Yu Yang

Merge branch 'gh-pages' of github.com:baidu/Paddle into gh-pages

API
===
Model Config API
----------------
.. toctree::
:maxdepth: 1
v2/model_configs.rst
Data API
--------
.. toctree::
:maxdepth: 1
v2/data.rst
Train API
---------
.. toctree::
:maxdepth: 1
v2/run_logic.rst
\ No newline at end of file
v2/run_logic.rst
===========
Activation
===========
Abs
===
.. automodule:: paddle.v2.activation
:members: Abs
:noindex:
Exp
===
.. automodule:: paddle.v2.activation
:members: Exp
:noindex:
Identity
========
.. automodule:: paddle.v2.activation
:members: Identity
:noindex:
Linear
======
.. automodule:: paddle.v2.activation
:members: Linear
:noindex:
Log
===
.. automodule:: paddle.v2.activation
:members: Log
:noindex:
Square
======
.. automodule:: paddle.v2.activation
:members: Square
:noindex:
Sigmoid
=======
.. automodule:: paddle.v2.activation
:members: Sigmoid
:noindex:
Softmax
=======
.. automodule:: paddle.v2.activation
:members: Softmax
:noindex:
SequenceSoftmax
===============
.. automodule:: paddle.v2.activation
:members: SequenceSoftmax
:noindex:
Relu
====
.. automodule:: paddle.v2.activation
:members: Relu
:noindex:
BRelu
=====
.. automodule:: paddle.v2.activation
:members: BRelu
:noindex:
SoftRelu
========
.. automodule:: paddle.v2.activation
:members: SoftRelu
:noindex:
Tanh
====
.. automodule:: paddle.v2.activation
:members: Tanh
:noindex:
STanh
=====
.. automodule:: paddle.v2.activation
:members: STanh
:noindex:
Parameter Attribute
===================
.. automodule:: paddle.v2.attr
:members:
:noindex:
.. _api_v2.layer:
======
Layers
======
Data layer
===========
.. _api_v2.layer_data:
data
----
.. automodule:: paddle.v2.layer
:members: data
:noindex:
Fully Connected Layers
======================
.. _api_v2.layer_fc:
fc
--
.. automodule:: paddle.v2.layer
:members: fc
:noindex:
selective_fc
------------
.. automodule:: paddle.v2.layer
:members: selective_fc
:noindex:
Conv Layers
===========
conv_operator
-------------
.. automodule:: paddle.v2.layer
:members: conv_operator
:noindex:
conv_projection
---------------
.. automodule:: paddle.v2.layer
:members: conv_projection
:noindex:
conv_shift
----------
.. automodule:: paddle.v2.layer
:members: conv_shift
:noindex:
img_conv
--------
.. automodule:: paddle.v2.layer
:members: img_conv
:noindex:
.. _api_v2.layer_context_projection:
context_projection
------------------
.. automodule:: paddle.v2.layer
:members: context_projection
:noindex:
Image Pooling Layer
===================
img_pool
--------
.. automodule:: paddle.v2.layer
:members: img_pool
:noindex:
spp
---
.. automodule:: paddle.v2.layer
:members: spp
:noindex:
maxout
------
.. automodule:: paddle.v2.layer
:members: maxout
:noindex:
Norm Layer
==========
img_cmrnorm
-----------
.. automodule:: paddle.v2.layer
:members: img_cmrnorm
:noindex:
batch_norm
----------
.. automodule:: paddle.v2.layer
:members: batch_norm
:noindex:
sum_to_one_norm
---------------
.. automodule:: paddle.v2.layer
:members: sum_to_one_norm
:noindex:
Recurrent Layers
================
recurrent
---------
.. automodule:: paddle.v2.layer
:members: recurrent
:noindex:
lstmemory
---------
.. automodule:: paddle.v2.layer
:members: lstmemory
:noindex:
grumemory
---------
.. automodule:: paddle.v2.layer
:members: grumemory
:noindex:
Recurrent Layer Group
=====================
memory
------
.. automodule:: paddle.v2.layer
:members: memory
:noindex:
recurrent_group
---------------
.. automodule:: paddle.v2.layer
:members: recurrent_group
:noindex:
lstm_step
---------
.. automodule:: paddle.v2.layer
:members: lstm_step
:noindex:
gru_step
--------
.. automodule:: paddle.v2.layer
:members: gru_step
:noindex:
beam_search
------------
.. automodule:: paddle.v2.layer
:members: beam_search
:noindex:
get_output
----------
.. automodule:: paddle.v2.layer
:members: get_output
:noindex:
Mixed Layer
===========
.. _api_v2.layer_mixed:
mixed
-----
.. automodule:: paddle.v2.layer
:members: mixed
:noindex:
.. _api_v2.layer_embedding:
embedding
---------
.. automodule:: paddle.v2.layer
:members: embedding
:noindex:
scaling_projection
------------------
.. automodule:: paddle.v2.layer
:members: scaling_projection
:noindex:
dotmul_projection
-----------------
.. automodule:: paddle.v2.layer
:members: dotmul_projection
:noindex:
dotmul_operator
---------------
.. automodule:: paddle.v2.layer
:members: dotmul_operator
:noindex:
full_matrix_projection
----------------------
.. automodule:: paddle.v2.layer
:members: full_matrix_projection
:noindex:
identity_projection
-------------------
.. automodule:: paddle.v2.layer
:members: identity_projection
:noindex:
table_projection
----------------
.. automodule:: paddle.v2.layer
:members: table_projection
:noindex:
trans_full_matrix_projection
----------------------------
.. automodule:: paddle.v2.layer
:members: trans_full_matrix_projection
:noindex:
Aggregate Layers
================
.. _api_v2.layer_pooling:
pooling
-------
.. automodule:: paddle.v2.layer
:members: pooling
:noindex:
.. _api_v2.layer_last_seq:
last_seq
--------
.. automodule:: paddle.v2.layer
:members: last_seq
:noindex:
.. _api_v2.layer_first_seq:
first_seq
---------
.. automodule:: paddle.v2.layer
:members: first_seq
:noindex:
concat
------
.. automodule:: paddle.v2.layer
:members: concat
:noindex:
seq_concat
----------
.. automodule:: paddle.v2.layer
:members: seq_concat
:noindex:
Reshaping Layers
================
block_expand
------------
.. automodule:: paddle.v2.layer
:members: block_expand
:noindex:
.. _api_v2.layer_expand:
expand
------
.. automodule:: paddle.v2.layer
:members: expand
:noindex:
repeat
------
.. automodule:: paddle.v2.layer
:members: repeat
:noindex:
rotate
------
.. automodule:: paddle.v2.layer
:members: rotate
:noindex:
seq_reshape
-----------
.. automodule:: paddle.v2.layer
:members: seq_reshape
:noindex:
Math Layers
===========
addto
-----
.. automodule:: paddle.v2.layer
:members: addto
:noindex:
linear_comb
-----------
.. automodule:: paddle.v2.layer
:members: linear_comb
:noindex:
interpolation
-------------
.. automodule:: paddle.v2.layer
:members: interpolation
:noindex:
bilinear_interp
---------------
.. automodule:: paddle.v2.layer
:members: bilinear_interp
:noindex:
power
-----
.. automodule:: paddle.v2.layer
:members: power
:noindex:
scaling
-------
.. automodule:: paddle.v2.layer
:members: scaling
:noindex:
slope_intercept
---------------
.. automodule:: paddle.v2.layer
:members: slope_intercept
:noindex:
tensor
------
.. automodule:: paddle.v2.layer
:members: tensor
:noindex:
.. _api_v2.layer_cos_sim:
cos_sim
-------
.. automodule:: paddle.v2.layer
:members: cos_sim
:noindex:
trans
-----
.. automodule:: paddle.v2.layer
:members: trans
:noindex:
Sampling Layers
===============
maxid
-----
.. automodule:: paddle.v2.layer
:members: maxid
:noindex:
sampling_id
-----------
.. automodule:: paddle.v2.layer
:members: sampling_id
:noindex:
Slicing and Joining Layers
==========================
pad
----
.. automodule:: paddle.v2.layer
:members: pad
:noindex:
.. _api_v2.layer_costs:
Cost Layers
===========
cross_entropy_cost
------------------
.. automodule:: paddle.v2.layer
:members: cross_entropy_cost
:noindex:
cross_entropy_with_selfnorm_cost
--------------------------------
.. automodule:: paddle.v2.layer
:members: cross_entropy_with_selfnorm_cost
:noindex:
multi_binary_label_cross_entropy_cost
-------------------------------------
.. automodule:: paddle.v2.layer
:members: multi_binary_label_cross_entropy_cost
:noindex:
huber_cost
----------
.. automodule:: paddle.v2.layer
:members: huber_cost
:noindex:
lambda_cost
-----------
.. automodule:: paddle.v2.layer
:members: lambda_cost
:noindex:
rank_cost
---------
.. automodule:: paddle.v2.layer
:members: rank_cost
:noindex:
sum_cost
---------
.. automodule:: paddle.v2.layer
:members: sum_cost
:noindex:
crf
---
.. automodule:: paddle.v2.layer
:members: crf
:noindex:
crf_decoding
------------
.. automodule:: paddle.v2.layer
:members: crf_decoding
:noindex:
ctc
---
.. automodule:: paddle.v2.layer
:members: ctc
:noindex:
warp_ctc
--------
.. automodule:: paddle.v2.layer
:members: warp_ctc
:noindex:
nce
---
.. automodule:: paddle.v2.layer
:members: nce
:noindex:
hsigmoid
---------
.. automodule:: paddle.v2.layer
:members: hsigmoid
:noindex:
Check Layer
============
eos
---
.. automodule:: paddle.v2.layer
:members: eos
:noindex:
========
Networks
========
The v2.networks module contains pieces of neural network that combine multiple layers.
NLP
===
sequence_conv_pool
------------------
.. automodule:: paddle.v2.networks
:members: sequence_conv_pool
:noindex:
.. _api_trainer_config_helpers_network_text_conv_pool:
text_conv_pool
--------------
.. automodule:: paddle.v2.networks
:members: text_conv_pool
:noindex:
Images
======
img_conv_bn_pool
----------------
.. automodule:: paddle.v2.networks
:members: img_conv_bn_pool
:noindex:
img_conv_group
--------------
.. automodule:: paddle.v2.networks
:members: img_conv_group
:noindex:
.. _api_trainer_config_helpers_network_simple_img_conv_pool:
simple_img_conv_pool
--------------------
.. automodule:: paddle.v2.networks
:members: simple_img_conv_pool
:noindex:
vgg_16_network
---------------
.. automodule:: paddle.v2.networks
:members: vgg_16_network
:noindex:
Recurrent
=========
LSTM
----
lstmemory_unit
``````````````
.. automodule:: paddle.v2.networks
:members: lstmemory_unit
:noindex:
lstmemory_group
```````````````
.. automodule:: paddle.v2.networks
:members: lstmemory_group
:noindex:
simple_lstm
```````````
.. automodule:: paddle.v2.networks
:members: simple_lstm
:noindex:
bidirectional_lstm
``````````````````
.. automodule:: paddle.v2.networks
:members: bidirectional_lstm
:noindex:
GRU
---
gru_unit
````````
.. automodule:: paddle.v2.networks
:members: gru_unit
:noindex:
gru_group
`````````
.. automodule:: paddle.v2.networks
:members: gru_group
:noindex:
simple_gru
``````````
.. automodule:: paddle.v2.networks
:members: simple_gru
:noindex:
simple_attention
----------------
.. automodule:: paddle.v2.networks
:members: simple_attention
:noindex:
Miscs
=====
dropout_layer
--------------
.. automodule:: paddle.v2.networks
:members: dropout_layer
:noindex:
.. _api_v2.optimizer:
==========
Optimizer
==========
Momentum
========
.. automodule:: paddle.v2.optimizer
:members: Momentum
:noindex:
Adam
====
.. automodule:: paddle.v2.optimizer
:members: Adam
:noindex:
Adamax
======
.. automodule:: paddle.v2.optimizer
:members: Adamax
:noindex:
AdaGrad
=======
.. automodule:: paddle.v2.optimizer
:members: AdaGrad
:noindex:
DecayedAdaGrad
==============
.. automodule:: paddle.v2.optimizer
:members: DecayedAdaGrad
:noindex:
AdaDelta
========
.. automodule:: paddle.v2.optimizer
:members: AdaDelta
:noindex:
RMSProp
=======
.. automodule:: paddle.v2.optimizer
:members: RMSProp
:noindex:
=======
Pooling
=======
BasePool
========
.. automodule:: paddle.v2.pooling
:members: BasePool
:noindex:
Avg
===
.. automodule:: paddle.v2.pooling
:members: Avg
:noindex:
Max
===
.. automodule:: paddle.v2.pooling
:members: Max
:noindex:
Sum
===
.. automodule:: paddle.v2.pooling
:members: Sum
:noindex:
SquareRootN
===========
.. automodule:: paddle.v2.pooling
:members: SquareRootN
:noindex:
CudnnAvg
========
.. automodule:: paddle.v2.pooling
:members: CudnnAvg
:noindex:
CudnnMax
========
.. automodule:: paddle.v2.pooling
:members: CudnnMax
:noindex:
================
Data Related API
================
========
Datasets
========
#########
DataTypes
#########
=========
.. automodule:: paddle.v2.data_type
:members:
:noindex:
##########
DataFeeder
##########
==========
.. automodule:: paddle.v2.data_feeder
:members:
:noindex:
######
Reader
######
======
.. automodule:: paddle.v2.reader
:members:
:noindex:
.. automodule:: paddle.v2.reader.creator
:members:
:noindex:
#########
minibatch
#########
=========
.. automodule:: paddle.v2.minibatch
:members:
:noindex:
#######
Dataset
#######
=======
.. automodule:: paddle.v2.dataset
:members:
:noindex:
mnist
+++++
.. automodule:: paddle.v2.dataset.mnist
:members:
:noindex:
cifar
......@@ -54,40 +55,54 @@ cifar
.. automodule:: paddle.v2.dataset.cifar
:members:
:noindex:
conll05
+++++++
.. automodule:: paddle.v2.dataset.conll05
:members:
:noindex:
imdb
++++
.. automodule:: paddle.v2.dataset.imdb
:members:
:noindex:
imikolov
++++++++
.. automodule:: paddle.v2.dataset.imikolov
:members:
:noindex:
movielens
+++++++++
.. automodule:: paddle.v2.dataset.movielens
:members:
:noindex:
sentiment
+++++++++
.. automodule:: paddle.v2.dataset.sentiment
:members:
:noindex:
uci_housing
+++++++++++
.. automodule:: paddle.v2.dataset.uci_housing
:members:
:noindex:
wmt14
+++++
.. automodule:: paddle.v2.dataset.uci_housing
:members:
:noindex:
#########################
Configuration Related API
#########################
======
Layers
======
.. automodule:: paddle.v2.layer
:members:
==========
Attributes
==========
.. automodule:: paddle.v2.attr
:members:
===========
Activations
===========
.. automodule:: paddle.v2.activation
:members:
========
Poolings
========
.. automodule:: paddle.v2.pooling
:members:
========
Networks
========
.. automodule:: paddle.v2.networks
:members:
==========
Optimizers
==========
.. automodule:: paddle.v2.optimizer
:members:
Model Configuration
===================
.. toctree::
:maxdepth: 1
config/activation.rst
config/layer.rst
config/optimizer.rst
config/pooling.rst
config/networks.rst
config/attr.rst
###########
Trainer API
###########
======================
Training and Inference
======================
==========
Parameters
==========
.. automodule:: paddle.v2.parameters
:members:
:noindex:
=======
Trainer
=======
.. automodule:: paddle.v2.trainer
:members:
.. automodule:: paddle.v2.trainer
:noindex:
=====
Event
=====
.. automodule:: paddle.v2.event
:members:
.. automodule:: paddle.v2.event
:noindex:
=========
Inference
=========
.. autofunction:: paddle.v2.infer
\ No newline at end of file
.. autofunction:: paddle.v2.infer
:noindex:
......@@ -9,6 +9,100 @@ Please be aware that you will need to change `Dockers settings
of your hardware resource on Mac OS X and Windows.
Usage of CPU-only and GPU Images
----------------------------------
For each version of PaddlePaddle, we release 2 Docker images, a
CPU-only one and a CUDA GPU one. We do so by configuring
`dockerhub.com <https://hub.docker.com/r/paddledev/paddle/>`_
automatically generate the latest docker images `paddledev/paddle:0.10.0rc1-cpu`
and `paddledev/paddle:0.10.0rc1-gpu`.
To run the CPU-only image as an interactive container:
.. code-block:: bash
docker run -it --rm paddledev/paddle:0.10.0rc1-cpu /bin/bash
or, we can run it as a daemon container
.. code-block:: bash
docker run -d -p 2202:22 -p 8888:8888 paddledev/paddle:0.10.0rc1-cpu
and SSH to this container using password :code:`root`:
.. code-block:: bash
ssh -p 2202 root@localhost
An advantage of using SSH is that we can connect to PaddlePaddle from
more than one terminals. For example, one terminal running vi and
another one running Python interpreter. Another advantage is that we
can run the PaddlePaddle container on a remote server and SSH to it
from a laptop.
Above methods work with the GPU image too -- just please don't forget
to install CUDA driver and let Docker knows about it:
.. code-block:: bash
export CUDA_SO="$(\ls /usr/lib64/libcuda* | xargs -I{} echo '-v {}:{}') $(\ls /usr/lib64/libnvidia* | xargs -I{} echo '-v {}:{}')"
export DEVICES=$(\ls /dev/nvidia* | xargs -I{} echo '--device {}:{}')
docker run ${CUDA_SO} ${DEVICES} -it paddledev/paddle:0.10.0rc1-gpu
PaddlePaddle Book
------------------
The Jupyter Notebook is an open-source web application that allows
you to create and share documents that contain live code, equations,
visualizations and explanatory text in a single browser.
PaddlePaddle Book is an interactive Jupyter Notebook for users and developers.
We already exposed port 8888 for this book. If you want to
dig deeper into deep learning, PaddlePaddle Book definitely is your best choice.
Once you are inside the container, simply issue the command:
.. code-block:: bash
jupyter notebook
Then, you would back and paste the address into the local browser:
.. code-block:: text
http://localhost:8888/
That's all. Enjoy your journey!
Non-AVX Images
--------------
Please be aware that the CPU-only and the GPU images both use the AVX
instruction set, but old computers produced before 2008 do not support
AVX. The following command checks if your Linux computer supports
AVX:
.. code-block:: bash
if cat /proc/cpuinfo | grep -i avx; then echo Yes; else echo No; fi
If it doesn't, we will need to build non-AVX images manually from
source code:
.. code-block:: bash
cd ~
git clone https://github.com/PaddlePaddle/Paddle.git
cd Paddle
docker build --build-arg WITH_AVX=OFF -t paddle:cpu-noavx -f paddle/scripts/docker/Dockerfile .
docker build --build-arg WITH_AVX=OFF -t paddle:gpu-noavx -f paddle/scripts/docker/Dockerfile.gpu .
Development Using Docker
------------------------
......@@ -82,103 +176,6 @@ Windows -- in a consistent way.
cd /paddle/build
ctest
4. Run PaddlePaddle Book under Docker Container
The Jupyter Notebook is an open-source web application that allows
you to create and share documents that contain live code, equations,
visualizations and explanatory text in a single browser.
PaddlePaddle Book is an interactive Jupyter Notebook for users and developers.
We already exposed port 8888 for this book. If you want to
dig deeper into deep learning, PaddlePaddle Book definitely is your best choice.
Once you are inside the container, simply issue the command:
.. code-block:: bash
jupyter notebook
Then, you would back and paste the address into the local browser:
.. code-block:: text
http://localhost:8888/
That's all. Enjoy your journey!
CPU-only and GPU Images
-----------------------
For each version of PaddlePaddle, we release 2 Docker images, a
CPU-only one and a CUDA GPU one. We do so by configuring
`dockerhub.com <https://hub.docker.com/r/paddledev/paddle/>`_
automatically runs the following commands:
.. code-block:: bash
docker build -t paddle:cpu -f paddle/scripts/docker/Dockerfile .
docker build -t paddle:gpu -f paddle/scripts/docker/Dockerfile.gpu .
To run the CPU-only image as an interactive container:
.. code-block:: bash
docker run -it --rm paddledev/paddle:cpu-latest /bin/bash
or, we can run it as a daemon container
.. code-block:: bash
docker run -d -p 2202:22 paddledev/paddle:cpu-latest
and SSH to this container using password :code:`root`:
.. code-block:: bash
ssh -p 2202 root@localhost
An advantage of using SSH is that we can connect to PaddlePaddle from
more than one terminals. For example, one terminal running vi and
another one running Python interpreter. Another advantage is that we
can run the PaddlePaddle container on a remote server and SSH to it
from a laptop.
Above methods work with the GPU image too -- just please don't forget
to install CUDA driver and let Docker knows about it:
.. code-block:: bash
export CUDA_SO="$(\ls /usr/lib64/libcuda* | xargs -I{} echo '-v {}:{}') $(\ls /usr/lib64/libnvidia* | xargs -I{} echo '-v {}:{}')"
export DEVICES=$(\ls /dev/nvidia* | xargs -I{} echo '--device {}:{}')
docker run ${CUDA_SO} ${DEVICES} -it paddledev/paddle:gpu-latest
Non-AVX Images
--------------
Please be aware that the CPU-only and the GPU images both use the AVX
instruction set, but old computers produced before 2008 do not support
AVX. The following command checks if your Linux computer supports
AVX:
.. code-block:: bash
if cat /proc/cpuinfo | grep -i avx; then echo Yes; else echo No; fi
If it doesn't, we will need to build non-AVX images manually from
source code:
.. code-block:: bash
cd ~
git clone https://github.com/PaddlePaddle/Paddle.git
cd Paddle
docker build --build-arg WITH_AVX=OFF -t paddle:cpu-noavx -f paddle/scripts/docker/Dockerfile .
docker build --build-arg WITH_AVX=OFF -t paddle:gpu-noavx -f paddle/scripts/docker/Dockerfile.gpu .
Documentation
-------------
......@@ -194,7 +191,7 @@ container:
.. code-block:: bash
docker run -d --name paddle-cpu-doc paddle:cpu
docker run -d --name paddle-cpu-doc paddle:0.10.0rc1-cpu
docker run -d --volumes-from paddle-cpu-doc -p 8088:80 nginx
......
......@@ -228,16 +228,6 @@ It looks like there are a lot of arguments. However, most of them are for develo
<td class="left"></td><td class="left"></td><td class="left">√</td><td class="left">√</td>
</tr>
<tr>
<td class="left" rowspan = "2">metric learning</td><td class="left">external</td>
<td class="left">√</td><td class="left">√</td><td class="left">√</td><td class="left">√</td>
</tr>
<tr>
<td class="left">data_server_port</td>
<td class="left"></td><td class="left">√</td><td class="left"></td><td class="left">√</td>
</tr>
<tr>
<td class="left" rowspan = "16">PServer</td><td class="left">start_pserver</td>
<td class="left"></td><td class="left">√</td><td class="left"></td><td class="left">√</td>
......
......@@ -184,15 +184,6 @@
- Specify shared dynamic library. It can be defined out of paddle by user.
- type: string (default: "", null).
## Metric Learning
* `--external`
- Whether to use external machine for metric learning.
- type: bool (default: 0).
* `--data_server_port`
- Listening port for dserver (data server), dserver is mainly used in metric learning.
- type: int32 (default: 21134).
## DataProvider
* `--memory_threshold_on_load_data`
......
* {
font-family:"Roboto","Lato","proxima-nova","Helvetica Neue",Arial,sans-serif;
}
body {
padding-top: 80px;
background-image: none !important;
......
......@@ -33,7 +33,7 @@
href="../genindex.html"/>
<link rel="search" title="Search" href="../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../index.html"/>
<link rel="prev" title="Trainer API" href="../api/v2/run_logic.html"/>
<link rel="prev" title="Training and Inference" href="../api/v2/run_logic.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../_static/css/override.css" type="text/css" />
......@@ -153,9 +153,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">ABOUT</a></li>
......@@ -216,7 +224,7 @@ We hope to build an active open source community both by providing feedback and
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../api/v2/run_logic.html" class="btn btn-neutral" title="Trainer API" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
<a href="../api/v2/run_logic.html" class="btn btn-neutral" title="Training and Inference" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
......
......@@ -33,7 +33,7 @@
href="../genindex.html"/>
<link rel="search" title="Search" href="../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../index.html"/>
<link rel="next" title="Configuration Related API" href="v2/model_configs.html"/>
<link rel="next" title="Model Configuration" href="v2/model_configs.html"/>
<link rel="prev" title="Tune GPU Performance" href="../howto/optimization/gpu_profiling_en.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
......@@ -154,9 +154,17 @@
</ul>
</li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../about/index_en.html">ABOUT</a></li>
......@@ -166,12 +174,7 @@
</nav>
<nav class="local-toc"><ul>
<li><a class="reference internal" href="#">API</a><ul>
<li><a class="reference internal" href="#model-config-api">Model Config API</a></li>
<li><a class="reference internal" href="#data-api">Data API</a></li>
<li><a class="reference internal" href="#train-api">Train API</a></li>
</ul>
</li>
<li><a class="reference internal" href="#">API</a></li>
</ul>
</nav>
......@@ -201,30 +204,13 @@
<div class="section" id="api">
<h1>API<a class="headerlink" href="#api" title="Permalink to this headline"></a></h1>
<div class="section" id="model-config-api">
<h2>Model Config API<a class="headerlink" href="#model-config-api" title="Permalink to this headline"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l1"><a class="reference internal" href="v2/model_configs.html">Model Configuration</a></li>
<li class="toctree-l1"><a class="reference internal" href="v2/data.html">Datasets</a></li>
<li class="toctree-l1"><a class="reference internal" href="v2/run_logic.html">Training and Inference</a></li>
</ul>
</div>
</div>
<div class="section" id="data-api">
<h2>Data API<a class="headerlink" href="#data-api" title="Permalink to this headline"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="v2/data.html">Data Related API</a></li>
</ul>
</div>
</div>
<div class="section" id="train-api">
<h2>Train API<a class="headerlink" href="#train-api" title="Permalink to this headline"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="v2/run_logic.html">Trainer API</a></li>
</ul>
</div>
</div>
</div>
......@@ -234,7 +220,7 @@
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="v2/model_configs.html" class="btn btn-neutral float-right" title="Configuration Related API" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="v2/model_configs.html" class="btn btn-neutral float-right" title="Model Configuration" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="../howto/optimization/gpu_profiling_en.html" class="btn btn-neutral" title="Tune GPU Performance" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......@@ -264,9 +272,9 @@ None if user don&#8217;t care.</li>
<li><strong>fc_act</strong> (<em>BaseActivation</em>) &#8211; fc layer activation type. None means tanh</li>
<li><strong>pool_bias_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ParameterAttribute" title="paddle.trainer_config_helpers.attrs.ParameterAttribute"><em>ParameterAttribute</em></a><em> or </em><em>None.</em>) &#8211; pooling layer bias attr. None if don&#8217;t care.
False if no bias.</li>
<li><strong>fc_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; fc layer extra attribute.</li>
<li><strong>context_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; context projection layer extra attribute.</li>
<li><strong>pool_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; pooling layer extra attribute.</li>
<li><strong>fc_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; fc layer extra attribute.</li>
<li><strong>context_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; context projection layer extra attribute.</li>
<li><strong>pool_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; pooling layer extra attribute.</li>
</ul>
</td>
</tr>
......@@ -312,9 +320,9 @@ None if user don&#8217;t care.</li>
<li><strong>fc_act</strong> (<em>BaseActivation</em>) &#8211; fc layer activation type. None means tanh</li>
<li><strong>pool_bias_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ParameterAttribute" title="paddle.trainer_config_helpers.attrs.ParameterAttribute"><em>ParameterAttribute</em></a><em> or </em><em>None.</em>) &#8211; pooling layer bias attr. None if don&#8217;t care.
False if no bias.</li>
<li><strong>fc_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; fc layer extra attribute.</li>
<li><strong>context_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; context projection layer extra attribute.</li>
<li><strong>pool_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; pooling layer extra attribute.</li>
<li><strong>fc_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; fc layer extra attribute.</li>
<li><strong>context_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; context projection layer extra attribute.</li>
<li><strong>pool_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; pooling layer extra attribute.</li>
</ul>
</td>
</tr>
......@@ -363,7 +371,7 @@ False if no bias.</li>
<li><strong>bn_layer_attr</strong> &#8211; ParameterAttribute.</li>
<li><strong>pool_stride</strong> (<em>int</em>) &#8211; see img_pool_layer&#8217;s document.</li>
<li><strong>pool_padding</strong> (<em>int</em>) &#8211; see img_pool_layer&#8217;s document.</li>
<li><strong>pool_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_pool_layer&#8217;s document.</li>
<li><strong>pool_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_pool_layer&#8217;s document.</li>
</ul>
</td>
</tr>
......@@ -438,10 +446,10 @@ False if no bias.</li>
<li><strong>num_channel</strong> (<em>int</em>) &#8211; see img_conv_layer for details</li>
<li><strong>param_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ParameterAttribute" title="paddle.trainer_config_helpers.attrs.ParameterAttribute"><em>ParameterAttribute</em></a>) &#8211; see img_conv_layer for details</li>
<li><strong>shared_bias</strong> (<em>bool</em>) &#8211; see img_conv_layer for details</li>
<li><strong>conv_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_conv_layer for details</li>
<li><strong>conv_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_conv_layer for details</li>
<li><strong>pool_stride</strong> (<em>int</em>) &#8211; see img_pool_layer for details</li>
<li><strong>pool_padding</strong> (<em>int</em>) &#8211; see img_pool_layer for details</li>
<li><strong>pool_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_pool_layer for details</li>
<li><strong>pool_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; see img_pool_layer for details</li>
</ul>
</td>
</tr>
......@@ -525,9 +533,9 @@ for more details about LSTM. The link goes as follows:
False means no bias, None means default bias.</li>
<li><strong>lstm_bias_attr</strong> (<em>ParameterAttribute|False</em>) &#8211; bias parameter attribute of lstm layer.
False means no bias, None means default bias.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
<li><strong>get_output_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; get output layer&#8217;s extra attribute.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
<li><strong>get_output_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; get output layer&#8217;s extra attribute.</li>
</ul>
</td>
</tr>
......@@ -586,9 +594,9 @@ full_matrix_projection must be included before lstmemory_unit is called.</p>
False means no bias, None means default bias.</li>
<li><strong>lstm_bias_attr</strong> (<em>ParameterAttribute|False</em>) &#8211; bias parameter attribute of lstm layer.
False means no bias, None means default bias.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
<li><strong>get_output_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; get output layer&#8217;s extra attribute.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
<li><strong>get_output_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; get output layer&#8217;s extra attribute.</li>
</ul>
</td>
</tr>
......@@ -631,8 +639,8 @@ means default bias.</li>
<li><strong>act</strong> (<em>BaseActivation</em>) &#8211; lstm final activiation type</li>
<li><strong>gate_act</strong> (<em>BaseActivation</em>) &#8211; lstm gate activiation type</li>
<li><strong>state_act</strong> (<em>BaseActivation</em>) &#8211; lstm state activiation type.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_cell_attr</strong> (<a class="reference internal" href="../../v2/model_configs.html#paddle.v2.attr.ExtraLayerAttribute" title="paddle.v2.attr.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
<li><strong>mixed_layer_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; mixed layer&#8217;s extra attribute.</li>
<li><strong>lstm_cell_attr</strong> (<a class="reference internal" href="attrs.html#paddle.trainer_config_helpers.attrs.ExtraLayerAttribute" title="paddle.trainer_config_helpers.attrs.ExtraLayerAttribute"><em>ExtraLayerAttribute</em></a>) &#8211; lstm layer&#8217;s extra attribute.</li>
</ul>
</td>
</tr>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
......
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Activation &mdash; PaddlePaddle documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/>
<link rel="up" title="Model Configuration" href="../model_configs.html"/>
<link rel="next" title="Layers" href="layer.html"/>
<link rel="prev" title="Model Configuration" href="../model_configs.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
<script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<header class="site-header">
<div class="site-logo">
<a href="/"><img src="../../../_static/images/PP_w.png"></a>
</div>
<div class="site-nav-links">
<div class="site-menu">
<a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
<div class="language-switcher dropdown">
<a type="button" data-toggle="dropdown">
<span>English</span>
<i class="fa fa-angle-up"></i>
<i class="fa fa-angle-down"></i>
</a>
<ul class="dropdown-menu">
<li><a href="/doc_cn">中文</a></li>
<li><a href="/doc">English</a></li>
</ul>
</div>
<ul class="site-page-links">
<li><a>Home</a></li>
<li><a>Get Started</a></li>
<li class="active"><a>Documentation</a></li>
<li><a>About Us</a></li>
</ul>
</div>
<div class="doc-module">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
</header>
<div class="main-content-wrap">
<nav class="doc-menu-vertical" role="navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/basic_usage/index_en.html">Simple Linear Regression</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/quick_start/index_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/rec/ml_regression_en.html">MovieLens Regression</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/image_classification/index_en.html">Image Classification</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/sentiment_analysis/index_en.html">Sentiment Analysis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/semantic_role_labeling/index_en.html">Semantic Role Labeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/text_generation/index_en.html">Text Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gan/index_en.html">Image Auto-Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/imagenet_model/resnet_model_en.html">ImageNet: ResNet</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/embedding_model/index_en.html">Embedding: Chinese Word</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="../model_configs.html">Model Configuration</a><ul class="current">
<li class="toctree-l3 current"><a class="current reference internal" href="#">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
</nav>
<nav class="local-toc"><ul>
<li><a class="reference internal" href="#">Activation</a><ul>
<li><a class="reference internal" href="#abs">Abs</a></li>
<li><a class="reference internal" href="#exp">Exp</a></li>
<li><a class="reference internal" href="#identity">Identity</a></li>
<li><a class="reference internal" href="#linear">Linear</a></li>
<li><a class="reference internal" href="#log">Log</a></li>
<li><a class="reference internal" href="#square">Square</a></li>
<li><a class="reference internal" href="#sigmoid">Sigmoid</a></li>
<li><a class="reference internal" href="#softmax">Softmax</a></li>
<li><a class="reference internal" href="#sequencesoftmax">SequenceSoftmax</a></li>
<li><a class="reference internal" href="#relu">Relu</a></li>
<li><a class="reference internal" href="#brelu">BRelu</a></li>
<li><a class="reference internal" href="#softrelu">SoftRelu</a></li>
<li><a class="reference internal" href="#tanh">Tanh</a></li>
<li><a class="reference internal" href="#stanh">STanh</a></li>
</ul>
</li>
</ul>
</nav>
<section class="doc-content-wrap">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index_en.html">API</a> > </li>
<li><a href="../model_configs.html">Model Configuration</a> > </li>
<li>Activation</li>
</ul>
</div>
<div class="wy-nav-content" id="doc-content">
<div class="rst-content">
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="activation">
<h1>Activation<a class="headerlink" href="#activation" title="Permalink to this headline"></a></h1>
<div class="section" id="abs">
<h2>Abs<a class="headerlink" href="#abs" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Abs</code></dt>
<dd><p>Abs Activation.</p>
<p>Forward: <span class="math">\(f(z) = abs(z)\)</span></p>
<p>Derivative:</p>
<div class="math">
\[\begin{split}1 &amp;\quad if \quad z &gt; 0 \\
-1 &amp;\quad if \quad z &lt; 0 \\
0 &amp;\quad if \quad z = 0\end{split}\]</div>
</dd></dl>
</div>
<div class="section" id="exp">
<h2>Exp<a class="headerlink" href="#exp" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Exp</code></dt>
<dd><p>Exponential Activation.</p>
<div class="math">
\[f(z) = e^z.\]</div>
</dd></dl>
</div>
<div class="section" id="identity">
<h2>Identity<a class="headerlink" href="#identity" title="Permalink to this headline"></a></h2>
<dl class="attribute">
<dt>
<code class="descclassname">paddle.v2.activation.</code><code class="descname">Identity</code></dt>
<dd><p>alias of <code class="xref py py-class docutils literal"><span class="pre">Linear</span></code></p>
</dd></dl>
</div>
<div class="section" id="linear">
<h2>Linear<a class="headerlink" href="#linear" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Linear</code></dt>
<dd><p>Identity Activation.</p>
<p>Just do nothing for output both forward/backward.</p>
</dd></dl>
</div>
<div class="section" id="log">
<h2>Log<a class="headerlink" href="#log" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Log</code></dt>
<dd><p>Logarithm Activation.</p>
<div class="math">
\[f(z) = log(z)\]</div>
</dd></dl>
</div>
<div class="section" id="square">
<h2>Square<a class="headerlink" href="#square" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Square</code></dt>
<dd><p>Square Activation.</p>
<div class="math">
\[f(z) = z^2.\]</div>
</dd></dl>
</div>
<div class="section" id="sigmoid">
<h2>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Sigmoid</code></dt>
<dd><p>Sigmoid activation.</p>
<div class="math">
\[f(z) = \frac{1}{1+exp(-z)}\]</div>
</dd></dl>
</div>
<div class="section" id="softmax">
<h2>Softmax<a class="headerlink" href="#softmax" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Softmax</code></dt>
<dd><p>Softmax activation for simple input</p>
<div class="math">
\[P(y=j|x) = \frac{e^{x_j}} {\sum^K_{k=1} e^{x_j} }\]</div>
</dd></dl>
</div>
<div class="section" id="sequencesoftmax">
<h2>SequenceSoftmax<a class="headerlink" href="#sequencesoftmax" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">SequenceSoftmax</code></dt>
<dd><p>Softmax activation for one sequence. The dimension of input feature must be
1 and a sequence.</p>
<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">result</span> <span class="o">=</span> <span class="n">softmax</span><span class="p">(</span><span class="k">for</span> <span class="n">each_feature_vector</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="n">input_feature</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">each_time_step_output</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">output</span><span class="p">):</span>
<span class="n">each_time_step_output</span> <span class="o">=</span> <span class="n">result</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
</pre></div>
</div>
</dd></dl>
</div>
<div class="section" id="relu">
<h2>Relu<a class="headerlink" href="#relu" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Relu</code></dt>
<dd><p>Relu activation.</p>
<p>forward. <span class="math">\(y = max(0, z)\)</span></p>
<p>derivative:</p>
<div class="math">
\[\begin{split}1 &amp;\quad if z &gt; 0 \\
0 &amp;\quad\mathrm{otherwize}\end{split}\]</div>
</dd></dl>
</div>
<div class="section" id="brelu">
<h2>BRelu<a class="headerlink" href="#brelu" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">BRelu</code></dt>
<dd><p>BRelu Activation.</p>
<p>forward. <span class="math">\(y = min(24, max(0, z))\)</span></p>
<p>derivative:</p>
<div class="math">
\[\begin{split}1 &amp;\quad if 0 &lt; z &lt; 24 \\
0 &amp;\quad \mathrm{otherwise}\end{split}\]</div>
</dd></dl>
</div>
<div class="section" id="softrelu">
<h2>SoftRelu<a class="headerlink" href="#softrelu" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">SoftRelu</code></dt>
<dd><p>SoftRelu Activation.</p>
</dd></dl>
</div>
<div class="section" id="tanh">
<h2>Tanh<a class="headerlink" href="#tanh" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">Tanh</code></dt>
<dd><p>Tanh activation.</p>
<div class="math">
\[f(z)=tanh(z)=\frac{e^z-e^{-z}}{e^z+e^{-z}}\]</div>
</dd></dl>
</div>
<div class="section" id="stanh">
<h2>STanh<a class="headerlink" href="#stanh" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.activation.</code><code class="descname">STanh</code></dt>
<dd><p>Scaled Tanh Activation.</p>
<div class="math">
\[f(z) = 1.7159 * tanh(2/3*z)\]</div>
</dd></dl>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="layer.html" class="btn btn-neutral float-right" title="Layers" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="../model_configs.html" class="btn btn-neutral" title="Model Configuration" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright 2016, PaddlePaddle developers.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
<script src="../../../_static/js/paddle_doc_init.js"></script>
</body>
</html>
\ No newline at end of file
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Parameter Attribute &mdash; PaddlePaddle documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/>
<link rel="up" title="Model Configuration" href="../model_configs.html"/>
<link rel="next" title="Datasets" href="../data.html"/>
<link rel="prev" title="Networks" href="networks.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
<script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<header class="site-header">
<div class="site-logo">
<a href="/"><img src="../../../_static/images/PP_w.png"></a>
</div>
<div class="site-nav-links">
<div class="site-menu">
<a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
<div class="language-switcher dropdown">
<a type="button" data-toggle="dropdown">
<span>English</span>
<i class="fa fa-angle-up"></i>
<i class="fa fa-angle-down"></i>
</a>
<ul class="dropdown-menu">
<li><a href="/doc_cn">中文</a></li>
<li><a href="/doc">English</a></li>
</ul>
</div>
<ul class="site-page-links">
<li><a>Home</a></li>
<li><a>Get Started</a></li>
<li class="active"><a>Documentation</a></li>
<li><a>About Us</a></li>
</ul>
</div>
<div class="doc-module">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
</header>
<div class="main-content-wrap">
<nav class="doc-menu-vertical" role="navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/basic_usage/index_en.html">Simple Linear Regression</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/quick_start/index_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/rec/ml_regression_en.html">MovieLens Regression</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/image_classification/index_en.html">Image Classification</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/sentiment_analysis/index_en.html">Sentiment Analysis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/semantic_role_labeling/index_en.html">Semantic Role Labeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/text_generation/index_en.html">Text Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gan/index_en.html">Image Auto-Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/imagenet_model/resnet_model_en.html">ImageNet: ResNet</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/embedding_model/index_en.html">Embedding: Chinese Word</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="../model_configs.html">Model Configuration</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="networks.html">Networks</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
</nav>
<nav class="local-toc"><ul>
<li><a class="reference internal" href="#">Parameter Attribute</a></li>
</ul>
</nav>
<section class="doc-content-wrap">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index_en.html">API</a> > </li>
<li><a href="../model_configs.html">Model Configuration</a> > </li>
<li>Parameter Attribute</li>
</ul>
</div>
<div class="wy-nav-content" id="doc-content">
<div class="rst-content">
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="parameter-attribute">
<h1>Parameter Attribute<a class="headerlink" href="#parameter-attribute" title="Permalink to this headline"></a></h1>
<dl class="attribute">
<dt>
<code class="descclassname">paddle.v2.attr.</code><code class="descname">Param</code></dt>
<dd><p>alias of <code class="xref py py-class docutils literal"><span class="pre">ParameterAttribute</span></code></p>
</dd></dl>
<dl class="attribute">
<dt>
<code class="descclassname">paddle.v2.attr.</code><code class="descname">Extra</code></dt>
<dd><p>alias of <code class="xref py py-class docutils literal"><span class="pre">ExtraLayerAttribute</span></code></p>
</dd></dl>
<dl class="attribute">
<dt>
<code class="descclassname">paddle.v2.attr.</code><code class="descname">ParamAttr</code></dt>
<dd><p>alias of <code class="xref py py-class docutils literal"><span class="pre">ParameterAttribute</span></code></p>
</dd></dl>
<dl class="attribute">
<dt>
<code class="descclassname">paddle.v2.attr.</code><code class="descname">ExtraAttr</code></dt>
<dd><p>alias of <code class="xref py py-class docutils literal"><span class="pre">ExtraLayerAttribute</span></code></p>
</dd></dl>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.attr.</code><code class="descname">ParameterAttribute</code><span class="sig-paren">(</span><em>name=None</em>, <em>is_static=False</em>, <em>initial_std=None</em>, <em>initial_mean=None</em>, <em>initial_max=None</em>, <em>initial_min=None</em>, <em>l1_rate=None</em>, <em>l2_rate=None</em>, <em>learning_rate=None</em>, <em>momentum=None</em>, <em>gradient_clipping_threshold=None</em>, <em>sparse_update=False</em><span class="sig-paren">)</span></dt>
<dd><p>Parameter Attributes object. To fine-tuning network training process, user
can set attribute to control training details, such as l1,l2 rate / learning
rate / how to init param.</p>
<p>NOTE: IT IS A HIGH LEVEL USER INTERFACE.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>is_static</strong> (<em>bool</em>) &#8211; True if this parameter will be fixed while training.</li>
<li><strong>initial_std</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; Gauss Random initialization standard deviation.
None if not using Gauss Random initialize parameter.</li>
<li><strong>initial_mean</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; Gauss Random initialization mean.
None if not using Gauss Random initialize parameter.</li>
<li><strong>initial_max</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; Uniform initialization max value.</li>
<li><strong>initial_min</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; Uniform initialization min value.</li>
<li><strong>l1_rate</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; the l1 regularization factor</li>
<li><strong>l2_rate</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; the l2 regularization factor</li>
<li><strong>learning_rate</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; The parameter learning rate. None means 1.
The learning rate when optimize is LEARNING_RATE =
GLOBAL_LEARNING_RATE * PARAMETER_LEARNING_RATE
* SCHEDULER_FACTOR.</li>
<li><strong>momentum</strong> (<em>float</em><em> or </em><em>None</em>) &#8211; The parameter momentum. None means use global value.</li>
<li><strong>gradient_clipping_threshold</strong> (<em>float</em>) &#8211; gradient clipping threshold. If gradient
value larger than some value, will be
clipped.</li>
<li><strong>sparse_update</strong> (<em>bool</em>) &#8211; Enable sparse update for this parameter. It will
enable both local and remote sparse update.</li>
</ul>
</td>
</tr>
</tbody>
</table>
<dl class="method">
<dt>
<code class="descname">set_default_parameter_name</code><span class="sig-paren">(</span><em>name</em><span class="sig-paren">)</span></dt>
<dd><p>Set default parameter name. If parameter not set, then will use default
parameter name.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>name</strong> (<em>basestring</em>) &#8211; default parameter name.</td>
</tr>
</tbody>
</table>
</dd></dl>
</dd></dl>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.attr.</code><code class="descname">ExtraLayerAttribute</code><span class="sig-paren">(</span><em>error_clipping_threshold=None</em>, <em>drop_rate=None</em>, <em>device=None</em><span class="sig-paren">)</span></dt>
<dd><p>Some high level layer attributes config. You can set all attributes here,
but some layer doesn&#8217;t support all attributes. If you set an attribute to a
layer that not support this attribute, paddle will print an error and core.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>error_clipping_threshold</strong> (<em>float</em>) &#8211; Error clipping threshold.</li>
<li><strong>drop_rate</strong> (<em>float</em>) &#8211; Dropout rate. Dropout will create a mask on layer output.
The dropout rate is the zero rate of this mask. The
details of what dropout is please refer to <a class="reference external" href="https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf">here</a>.</li>
<li><strong>device</strong> (<em>int</em>) &#8211; <p>device ID of layer. device=-1, use CPU. device&gt;0, use GPU.
The details allocation in parallel_nn please refer to <a class="reference external" href="http://www.paddlepaddle.org/doc/ui/cmd_argument/use_case.html#case-2-specify-layers-in-different-devices">here</a>.</p>
</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../data.html" class="btn btn-neutral float-right" title="Datasets" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="networks.html" class="btn btn-neutral" title="Networks" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright 2016, PaddlePaddle developers.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
<script src="../../../_static/js/paddle_doc_init.js"></script>
</body>
</html>
\ No newline at end of file
此差异已折叠。
此差异已折叠。
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Optimizer &mdash; PaddlePaddle documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/>
<link rel="up" title="Model Configuration" href="../model_configs.html"/>
<link rel="next" title="Pooling" href="pooling.html"/>
<link rel="prev" title="Layers" href="layer.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
<script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<header class="site-header">
<div class="site-logo">
<a href="/"><img src="../../../_static/images/PP_w.png"></a>
</div>
<div class="site-nav-links">
<div class="site-menu">
<a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
<div class="language-switcher dropdown">
<a type="button" data-toggle="dropdown">
<span>English</span>
<i class="fa fa-angle-up"></i>
<i class="fa fa-angle-down"></i>
</a>
<ul class="dropdown-menu">
<li><a href="/doc_cn">中文</a></li>
<li><a href="/doc">English</a></li>
</ul>
</div>
<ul class="site-page-links">
<li><a>Home</a></li>
<li><a>Get Started</a></li>
<li class="active"><a>Documentation</a></li>
<li><a>About Us</a></li>
</ul>
</div>
<div class="doc-module">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
</header>
<div class="main-content-wrap">
<nav class="doc-menu-vertical" role="navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/basic_usage/index_en.html">Simple Linear Regression</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/quick_start/index_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/rec/ml_regression_en.html">MovieLens Regression</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/image_classification/index_en.html">Image Classification</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/sentiment_analysis/index_en.html">Sentiment Analysis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/semantic_role_labeling/index_en.html">Semantic Role Labeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/text_generation/index_en.html">Text Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gan/index_en.html">Image Auto-Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/imagenet_model/resnet_model_en.html">ImageNet: ResNet</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/embedding_model/index_en.html">Embedding: Chinese Word</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="../model_configs.html">Model Configuration</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="layer.html">Layers</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
</nav>
<nav class="local-toc"><ul>
<li><a class="reference internal" href="#">Optimizer</a><ul>
<li><a class="reference internal" href="#momentum">Momentum</a></li>
<li><a class="reference internal" href="#adam">Adam</a></li>
<li><a class="reference internal" href="#adamax">Adamax</a></li>
<li><a class="reference internal" href="#adagrad">AdaGrad</a></li>
<li><a class="reference internal" href="#decayedadagrad">DecayedAdaGrad</a></li>
<li><a class="reference internal" href="#adadelta">AdaDelta</a></li>
<li><a class="reference internal" href="#rmsprop">RMSProp</a></li>
</ul>
</li>
</ul>
</nav>
<section class="doc-content-wrap">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index_en.html">API</a> > </li>
<li><a href="../model_configs.html">Model Configuration</a> > </li>
<li>Optimizer</li>
</ul>
</div>
<div class="wy-nav-content" id="doc-content">
<div class="rst-content">
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="optimizer">
<span id="api-v2-optimizer"></span><h1>Optimizer<a class="headerlink" href="#optimizer" title="Permalink to this headline"></a></h1>
<div class="section" id="momentum">
<h2>Momentum<a class="headerlink" href="#momentum" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="adam">
<h2>Adam<a class="headerlink" href="#adam" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="adamax">
<h2>Adamax<a class="headerlink" href="#adamax" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="adagrad">
<h2>AdaGrad<a class="headerlink" href="#adagrad" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="decayedadagrad">
<h2>DecayedAdaGrad<a class="headerlink" href="#decayedadagrad" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="adadelta">
<h2>AdaDelta<a class="headerlink" href="#adadelta" title="Permalink to this headline"></a></h2>
</div>
<div class="section" id="rmsprop">
<h2>RMSProp<a class="headerlink" href="#rmsprop" title="Permalink to this headline"></a></h2>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="pooling.html" class="btn btn-neutral float-right" title="Pooling" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="layer.html" class="btn btn-neutral" title="Layers" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright 2016, PaddlePaddle developers.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
<script src="../../../_static/js/paddle_doc_init.js"></script>
</body>
</html>
\ No newline at end of file
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Pooling &mdash; PaddlePaddle documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/>
<link rel="up" title="Model Configuration" href="../model_configs.html"/>
<link rel="next" title="Networks" href="networks.html"/>
<link rel="prev" title="Optimizer" href="optimizer.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
<script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<header class="site-header">
<div class="site-logo">
<a href="/"><img src="../../../_static/images/PP_w.png"></a>
</div>
<div class="site-nav-links">
<div class="site-menu">
<a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
<div class="language-switcher dropdown">
<a type="button" data-toggle="dropdown">
<span>English</span>
<i class="fa fa-angle-up"></i>
<i class="fa fa-angle-down"></i>
</a>
<ul class="dropdown-menu">
<li><a href="/doc_cn">中文</a></li>
<li><a href="/doc">English</a></li>
</ul>
</div>
<ul class="site-page-links">
<li><a>Home</a></li>
<li><a>Get Started</a></li>
<li class="active"><a>Documentation</a></li>
<li><a>About Us</a></li>
</ul>
</div>
<div class="doc-module">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
</header>
<div class="main-content-wrap">
<nav class="doc-menu-vertical" role="navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/basic_usage/index_en.html">Simple Linear Regression</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index_en.html">TUTORIALS</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/quick_start/index_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/rec/ml_regression_en.html">MovieLens Regression</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/image_classification/index_en.html">Image Classification</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/sentiment_analysis/index_en.html">Sentiment Analysis</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/semantic_role_labeling/index_en.html">Semantic Role Labeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/text_generation/index_en.html">Text Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/gan/index_en.html">Image Auto-Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/imagenet_model/resnet_model_en.html">ImageNet: ResNet</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../tutorials/embedding_model/index_en.html">Embedding: Chinese Word</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="../model_configs.html">Model Configuration</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="optimizer.html">Optimizer</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
</ul>
</nav>
<nav class="local-toc"><ul>
<li><a class="reference internal" href="#">Pooling</a><ul>
<li><a class="reference internal" href="#basepool">BasePool</a></li>
<li><a class="reference internal" href="#avg">Avg</a></li>
<li><a class="reference internal" href="#max">Max</a></li>
<li><a class="reference internal" href="#sum">Sum</a></li>
<li><a class="reference internal" href="#squarerootn">SquareRootN</a></li>
<li><a class="reference internal" href="#cudnnavg">CudnnAvg</a></li>
<li><a class="reference internal" href="#cudnnmax">CudnnMax</a></li>
</ul>
</li>
</ul>
</nav>
<section class="doc-content-wrap">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index_en.html">API</a> > </li>
<li><a href="../model_configs.html">Model Configuration</a> > </li>
<li>Pooling</li>
</ul>
</div>
<div class="wy-nav-content" id="doc-content">
<div class="rst-content">
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="pooling">
<h1>Pooling<a class="headerlink" href="#pooling" title="Permalink to this headline"></a></h1>
<div class="section" id="basepool">
<h2>BasePool<a class="headerlink" href="#basepool" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">BasePool</code><span class="sig-paren">(</span><em>name</em><span class="sig-paren">)</span></dt>
<dd><p>Base Pooling Type.
Note these pooling types are used for sequence input, not for images.
Each PoolingType contains one parameter:</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>name</strong> (<em>basestring</em>) &#8211; pooling layer type name used by paddle.</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
<div class="section" id="avg">
<h2>Avg<a class="headerlink" href="#avg" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">Avg</code><span class="sig-paren">(</span><em>strategy='average'</em><span class="sig-paren">)</span></dt>
<dd><p>Average pooling.</p>
<p>Return the average values for each dimension in sequence or time steps.</p>
<div class="math">
\[sum(samples\_of\_a\_sequence)/sample\_num\]</div>
</dd></dl>
</div>
<div class="section" id="max">
<h2>Max<a class="headerlink" href="#max" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">Max</code><span class="sig-paren">(</span><em>output_max_index=None</em><span class="sig-paren">)</span></dt>
<dd><p>Max pooling.</p>
<p>Return the very large values for each dimension in sequence or time steps.</p>
<div class="math">
\[max(samples\_of\_a\_sequence)\]</div>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>output_max_index</strong> (<em>bool|None</em>) &#8211; True if output sequence max index instead of max
value. None means use default value in proto.</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
<div class="section" id="sum">
<h2>Sum<a class="headerlink" href="#sum" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">Sum</code></dt>
<dd><p>Sum pooling.</p>
<p>Return the sum values of each dimension in sequence or time steps.</p>
<div class="math">
\[sum(samples\_of\_a\_sequence)\]</div>
</dd></dl>
</div>
<div class="section" id="squarerootn">
<h2>SquareRootN<a class="headerlink" href="#squarerootn" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">SquareRootN</code></dt>
<dd><p>Square Root Pooling.</p>
<p>Return the square root values of each dimension in sequence or time steps.</p>
<div class="math">
\[sum(samples\_of\_a\_sequence)/sqrt(sample\_num)\]</div>
</dd></dl>
</div>
<div class="section" id="cudnnavg">
<h2>CudnnAvg<a class="headerlink" href="#cudnnavg" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">CudnnAvg</code></dt>
<dd><p>Cudnn average pooling only support GPU. Return the average value in the
pooling window.</p>
</dd></dl>
</div>
<div class="section" id="cudnnmax">
<h2>CudnnMax<a class="headerlink" href="#cudnnmax" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.pooling.</code><code class="descname">CudnnMax</code></dt>
<dd><p>Cudnn max pooling only support GPU. Return the maxinum value in the
pooling window.</p>
</dd></dl>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="networks.html" class="btn btn-neutral float-right" title="Networks" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="optimizer.html" class="btn btn-neutral" title="Optimizer" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright 2016, PaddlePaddle developers.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
<script src="../../../_static/js/paddle_doc_init.js"></script>
</body>
</html>
\ No newline at end of file
此差异已折叠。
此差异已折叠。
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../about/index_en.html">ABOUT</a></li>
......
......@@ -152,9 +152,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
此差异已折叠。
......@@ -155,9 +155,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
......@@ -155,9 +155,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
......@@ -155,9 +155,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
......@@ -155,9 +155,17 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Configuration Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Related API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Trainer API</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
......
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
Parameter Attribute
===================
.. automodule:: paddle.v2.attr
:members:
:noindex:
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册