m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into multigpumultinode

Browse Source
wangkuiyi-patch-2
typhoonzero 7 years ago
parent 063868fb88 535646cf25
commit d2760bdacd
272 changed files with 4514 additions and 1578 deletions
Show Stats Download Patch File Download Diff File

9
.gitignore vendored
Unescape View File

@ -25,12 +25,3 @@ third_party/
# clion workspace.
cmake-build-*
# generated while compiling
paddle/pybind/pybind.h
CMakeFiles
cmake_install.cmake
paddle/.timestamp
python/paddlepaddle.egg-info/
paddle/fluid/pybind/pybind.h
python/paddle/version.py

2
cmake/external/mklml.cmake vendored
Unescape View File

@ -28,7 +28,7 @@ INCLUDE(ExternalProject)
SET(MKLML_PROJECT "extern_mklml")
SET(MKLML_VER "mklml_lnx_2018.0.1.20171007")
SET(MKLML_URL "https://github.com/01org/mkl-dnn/releases/download/v0.11/${MKLML_VER}.tgz")
SET(MKLML_URL "http://paddlepaddledeps.bj.bcebos.com/${MKLML_VER}.tgz")
SET(MKLML_SOURCE_DIR "${THIRD_PARTY_PATH}/mklml")
SET(MKLML_DOWNLOAD_DIR "${MKLML_SOURCE_DIR}/src/${MKLML_PROJECT}")
SET(MKLML_DST_DIR "mklml")

4
cmake/external/snappystream.cmake vendored
Unescape View File

@ -54,5 +54,7 @@ add_library(snappystream STATIC IMPORTED GLOBAL)
set_property(TARGET snappystream PROPERTY IMPORTED_LOCATION
"${SNAPPYSTREAM_INSTALL_DIR}/lib/libsnappystream.a")
include_directories(${SNAPPYSTREAM_INCLUDE_DIR})
include_directories(${SNAPPYSTREAM_INCLUDE_DIR}) # For snappysteam to include its own headers.
include_directories(${THIRD_PARTY_PATH}/install) # For Paddle to include snappy stream headers.
add_dependencies(snappystream extern_snappystream)

3
cmake/external/warpctc.cmake vendored
Unescape View File

@ -62,7 +62,8 @@ ExternalProject_Add(
)
MESSAGE(STATUS "warp-ctc library: ${WARPCTC_LIBRARIES}")
INCLUDE_DIRECTORIES(${WARPCTC_INCLUDE_DIR})
INCLUDE_DIRECTORIES(${WARPCTC_INCLUDE_DIR}) # For warpctc code to include its headers.
INCLUDE_DIRECTORIES(${THIRD_PARTY_PATH}/install) # For Paddle code to include warpctc headers.
ADD_LIBRARY(warpctc SHARED IMPORTED GLOBAL)
SET_PROPERTY(TARGET warpctc PROPERTY IMPORTED_LOCATION ${WARPCTC_LIBRARIES})

3
cmake/external/zlib.cmake vendored
Unescape View File

@ -25,7 +25,8 @@ ELSE(WIN32)
SET(ZLIB_LIBRARIES "${ZLIB_INSTALL_DIR}/lib/libz.a" CACHE FILEPATH "zlib library." FORCE)
ENDIF(WIN32)
INCLUDE_DIRECTORIES(${ZLIB_INCLUDE_DIR})
INCLUDE_DIRECTORIES(${ZLIB_INCLUDE_DIR}) # For zlib code to include its own headers.
INCLUDE_DIRECTORIES(${THIRD_PARTY_PATH}/install) # For Paddle code to include zlib.h.
ExternalProject_Add(
extern_zlib

6
cmake/generic.cmake
Unescape View File

@ -251,7 +251,7 @@ function(cc_test TARGET_NAME)
add_dependencies(${TARGET_NAME} ${cc_test_DEPS} paddle_gtest_main paddle_memory gtest gflags glog)
add_test(NAME ${TARGET_NAME}
COMMAND ${TARGET_NAME} ${cc_test_ARGS}
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR})
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
endif()
endfunction(cc_test)
@ -561,9 +561,9 @@ function(py_test TARGET_NAME)
set(multiValueArgs SRCS DEPS ARGS ENVS)
cmake_parse_arguments(py_test "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
add_test(NAME ${TARGET_NAME}
COMMAND env PYTHONPATH=${PADDLE_PYTHON_BUILD_DIR}/lib-python ${py_test_ENVS}
COMMAND env PYTHONPATH=${PADDLE_BINARY_DIR}/python ${py_test_ENVS}
${PYTHON_EXECUTABLE} -u ${py_test_SRCS} ${py_test_ARGS}
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR})
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
endif()
endfunction()

4
doc/fluid/CMakeLists.txt
Unescape View File

@ -27,7 +27,7 @@ sphinx_add_target(paddle_fluid_docs
${CMAKE_CURRENT_SOURCE_DIR}
${SPHINX_HTML_DIR_EN})
add_dependencies(paddle_fluid_docs gen_proto_py)
add_dependencies(paddle_fluid_docs gen_proto_py paddle_python)
# configured documentation tools and intermediate build results
set(BINARY_BUILD_DIR_CN "${CMAKE_CURRENT_BINARY_DIR}/cn/_build")
@ -50,6 +50,6 @@ sphinx_add_target(paddle_fluid_docs_cn
${CMAKE_CURRENT_SOURCE_DIR}
${SPHINX_HTML_DIR_CN})
add_dependencies(paddle_fluid_docs_cn gen_proto_py)
add_dependencies(paddle_fluid_docs_cn gen_proto_py paddle_python)
add_subdirectory(api)

2
doc/fluid/api/CMakeLists.txt
Unescape View File

@ -19,4 +19,4 @@ sphinx_add_target(paddle_fluid_apis
${CMAKE_CURRENT_SOURCE_DIR}
${SPHINX_HTML_DIR_EN})
add_dependencies(paddle_fluid_apis gen_proto_py framework_py_proto copy_paddle_pybind)
add_dependencies(paddle_fluid_apis gen_proto_py framework_py_proto copy_paddle_pybind paddle_python)

6
doc/fluid/design/algorithm/parameter_average.md
Unescape View File

@ -5,9 +5,11 @@ In a large scale machine learning setup where the size of the training data is h
Polyak and Juditsky (1992) showed that the test performance of simple average of parameters obtained by Stochastic Gradient Descent (SGD) is as good as that of parameter values that are obtained by training the model over and over again, over the training dataset.
Hence, to accelerate the speed of Stochastic Gradient Descent, Averaged Stochastic Gradient Descent (ASGD) was proposed in Polyak and Juditsky (1992). For ASGD, the running average of parameters obtained by SGD, is used as the estimator for <img src="./images/theta_star.gif"/><br/> . The averaging is done as follows:
Hence, to accelerate the speed of Stochastic Gradient Descent, Averaged Stochastic Gradient Descent (ASGD) was proposed in Polyak and Juditsky (1992). For ASGD, the running average of parameters obtained by SGD, is used as the estimator for <img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/theta_star.gif"/><br/> . The averaging is done as follows:
![](./images/asgd.gif)
<p align="center">
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/asgd.gif"><br />
</p>
We propose averaging for any optimizer similar to how ASGD performs it, as mentioned above.

4
doc/fluid/design/concurrent/channel.md
Unescape View File

@ -114,13 +114,13 @@ current thread under two conditions:
#### Channel Send
<p align="center">
<img src="./images/channel_send.png"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/channel_send.png"/><br/>
</p>
#### Channel Receive
<p align="center">
<img src="./images/channel_recv.png"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/channel_recv.png"/><br/>
</p>
## Limitations and Considerations

4
doc/fluid/design/concurrent/concurrent_programming.md
Unescape View File

@ -23,21 +23,25 @@ The following table compares concepts in Fluid and Go
<td>user-defined functions </td>
<td>
<a href="https://github.com/PaddlePaddle/Paddle/tree/develop/python/paddle/fluid">layers</a></td>
<td></td>
</tr>
<tr>
<td>control-flow and built-in functions </td>
<td>
<a href="https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators">intrinsics/operators</a></td>
<td></td>
</tr>
<tr>
<td>goroutines, channels </td>
<td>
<a href="https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/framework/thread_pool.h">class ThreadPool</a></td>
<td></td>
</tr>
<tr>
<td>runtime </td>
<td>
<a href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/executor.h">class Executor</a></td>
<td></td>
</tr>
</tbody>
</table>

2
doc/fluid/design/concurrent/select_op.md
Unescape View File

@ -254,7 +254,7 @@ only one case will be executed.
### select_op flow
<p align="center">
<img src="./images/select_op_workflow.png"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/select_op_workflow.png"/><br/>
</p>
The select algorithm is inspired by golang's select routine. Please refer to

10
doc/fluid/design/dist_train/distributed_architecture.md
Unescape View File

@ -40,11 +40,11 @@ computation is only specified in Python code which sits outside of PaddlePaddle,
Similar to how a compiler uses an intermediate representation (IR) so that the programmer does not need to manually optimize their code for most of the cases, we can have an intermediate representation in PaddlePaddle as well. The compiler optimizes the IR as follows:
<img src="src/compiler.png"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/compiler.png"/>
PaddlePaddle can support model parallelism by converting the IR so that the user no longer needs to manually perform the computation and operations in the Python component:
<img src="src/paddle-compile.png"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/paddle-compile.png"/>
The IR for PaddlePaddle after refactoring is called a `Block`, it specifies the computation dependency graph and the variables used in the computation.
@ -60,7 +60,7 @@ For a detailed explanation, refer to this document -
The revamped distributed training architecture can address the above discussed limitations. Below is the illustration of how it does so:
<img src="src/distributed_architecture.png"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/distributed_architecture.png"/>
The major components are: *Python API*, *Distribute Transpiler* and *Remote Executor*.
@ -152,7 +152,7 @@ for data in train_reader():
`JobDesc` object describe the distributed job resource specification to run on
Cluster environment.
<img src="src/remote_executor.png" width="500" align="center" />
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/remote_executor.png" width="500" align="center" />
`RemoteExecutor.run` sends the `ProgramDesc` and
[TrainingJob](https://github.com/PaddlePaddle/cloud/blob/unreleased-tpr/doc/autoscale/README.md#training-job-resource)
@ -171,7 +171,7 @@ In the future, a more general placement algorithm should be implemented, which m
The local training architecture will be the same as the distributed training architecture, the difference is that everything runs locally, and there is just one PaddlePaddle runtime:
<img src="src/local_architecture.png"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/local_architecture.png"/>
### Training Data

4
doc/fluid/design/dist_train/multi_cpu.md
Unescape View File

@ -8,11 +8,11 @@ Op graph to a multi-CPU Op graph, and run `ParallelDo` Op to run the graph.
## Transpiler
<img src="src/multi-threads/single-thread@3x.png" width="300">
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/single-thread@3x.png" width="300">
After converted:
<img src="src/multi-threads/multi-threads@3x.png" width="1000">
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/multi-threads@3x.png" width="1000">
## Implement

7
doc/fluid/design/dist_train/parameter_server.md
Unescape View File

@ -41,11 +41,11 @@ We will need these OPs: *Send*, *Recv*, *Enqueue*, *Dequeue*.
Below is an example of converting the user defined graph to the
subgraphs for the trainer and the parameter server:
<img src="src/local-graph.png" width="300"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/local-graph.png" width="300"/>
After converting:
<img src="src/dist-graph.png" width="700"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/dist-graph.png" width="700"/>
1. The parameter variable W and its optimizer program are placed on the parameter server.
1. Operators are added to the program.
@ -69,8 +69,7 @@ In Fluid, we introduce [SelectedRows](../selected_rows.md) to represent a list o
non-zero gradient data. So when we do parameter optimization both locally and remotely,
we only need to send those non-zero rows to the optimizer operators:
<img src="src/sparse_update.png" width="700" />
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/sparse_update.png" width="700" />
### Benefits
- Model parallelism becomes easier to implement: it is an extension to

8
doc/fluid/design/dynamic_rnn/rnn.md
Unescape View File

@ -5,7 +5,7 @@ This document describes the RNN (Recurrent Neural Network) operator and how it i
## RNN Algorithm Implementation
<p align="center">
<img src="./rnn.jpg"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/rnn.jpg"/>
</p>
The above diagram shows an RNN unrolled into a full network.
@ -22,7 +22,7 @@ There are several important concepts here:
There could be local variables defined in each step-net. PaddlePaddle runtime realizes these variables in *step-scopes* which are created for each step.
<p align="center">
<img src="./rnn.png"/><br/>
<img src="https://github.com/PaddlePaddle/Paddle/tree/develop/doc/fluid/images/rnn.png"/><br/>
Figure 2 illustrates the RNN's data flow
</p>
@ -93,7 +93,7 @@ For example, we could have a 2-level RNN, where the top level corresponds to par
The following figure illustrates feeding in text into the lower level, one sentence at a step, and the feeding in step outputs to the top level. The final top level output is about the whole text.
<p align="center">
<img src="./2_level_rnn.png"/>
<img src="https://github.com/PaddlePaddle/Paddle/tree/develop/doc/fluid/images/2_level_rnn.png"/>
</p>
```python
@ -149,5 +149,5 @@ If the `output_all_steps` is set to False, it will only output the final time st
<p align="center">
<img src="./rnn_2level_data.png"/>
<img src="https://github.com/PaddlePaddle/Paddle/tree/develop/doc/fluid/images/rnn_2level_data.png"/>
</p>

4
doc/fluid/design/modules/batch_norm_op.md
Unescape View File

@ -66,7 +66,7 @@ As most C++ operators do, `batch_norm_op` is defined by inputs, outputs, attribu
The following graph showes the training computational process of `batch_norm_op`:
<img src="../images/batch_norm_op_kernel.png" width="800"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/batch_norm_op_kernel.png" width="800"/>
cudnn provides APIs to finish the whole series of computation, we can use them in our GPU kernel.
@ -124,7 +124,7 @@ for pass_id in range(PASS_NUM):
`is_infer` is an attribute. Once an operator is created, its attributes can not be changed. It suggests us that we shall maintain two `batch_norm_op` in the model, one's `is_infer` is `True`(we call it `infer_batch_norm_op`) and the other one's is `False`(we call it `train_batch_norm_op`). They share all parameters and variables, but be placed in two different branches. That is to say, if a network contains a `batch_norm_op`, it will fork into two branches, one go through `train_batch_norm_op` and the other one go through `infer_batch_norm_op`:
<div align=center>
<img src="../images/batch_norm_fork.png" width="500"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/batch_norm_fork.png" width="500"/>
</div>
Just like what is shown in the above graph, the net forks before `batch_norm_op` and will never merge again. All the operators after `batch_norm_op` will duplicate.

16
doc/fluid/design/modules/regularization.md
Unescape View File

@ -6,17 +6,17 @@ A central problem in machine learning is how to design an algorithm that will pe
### Parameter Norm Penalties
Most common regularization approaches in deep learning are based on limiting the capacity of the models by adding a parameter norm penalty to the objective function `J`. This is given as follows:
<img src="./images/loss_equation.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/loss_equation.png" align="center"/><br/>
The parameter `alpha` is a hyperparameter that weights the relative contribution of the norm penalty term, `omega`, relative to the standard objective function `J`.
The most commonly used norm penalties are the L2 norm penalty and the L1 norm penalty. These are given as follows:
##### L2 Regularization:
<img src="./images/l2_regularization.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/l2_regularization.png" align="center"/><br/>
##### L1 Regularization
<img src="./images/l1_regularization.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/l1_regularization.png" align="center"/><br/>
A much more detailed mathematical background of regularization can be found [here](http://www.deeplearningbook.org/contents/regularization.html).
@ -40,11 +40,11 @@ The idea of building ops for regularization is in sync with the refactored Paddl
Below is an example of a really simple feed forward neural network.
<img src="./images/feed_forward.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/feed_forward.png" align="center"/><br/>
The Python API will modify this computation graph to add regularization operators. The modified computation graph will look as follows:
<img src="./images/feed_forward_regularized.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/feed_forward_regularized.png" align="center"/><br/>
   
### Python API implementation for Regularization
@ -64,9 +64,3 @@ Since we want to create the regularization ops in a lazy manner, the regularizat
#### High-level API
In PaddlePaddle Python API, users will primarily rely on [layer functions](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/python_api.md#layer-function) to create neural network layers. Hence, we also need to provide regularization functionality in layer functions. The design of these APIs can be postponed for later right now. A good reference for these APIs can be found in [Keras](https://keras.io/regularizers/) and also by looking at Tensorflow in [`tf.contrib.layers`](https://www.tensorflow.org/api_guides/python/contrib.layers).

4
doc/fluid/design/network/deep_speech_2.md
Unescape View File

@ -116,7 +116,7 @@ The classical DS2 network contains 15 layers (from bottom to top):
- **One** CTC-loss layer
<div align="center">
<img src="images/ds2_network.png" width=350><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/ds2_network.png" width=350><br/>
Figure 1. Archetecture of Deep Speech 2 Network.
</div>
@ -208,7 +208,7 @@ TODO by Assignees
### Beam Search with CTC and LM
<div align="center">
<img src="images/beam_search.png" width=600><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/beam_search.png" width=600><br/>
Figure 2. Algorithm for CTC Beam Search Decoder.
</div>

2
doc/fluid/design/network/sequence_decoder.md
Unescape View File

@ -199,7 +199,7 @@ Packing the `selected_generation_scores` will get a `LoDTensor`, and each tail i
## LoD and shape changes during decoding
<p align="center">
<img src="./images/LOD-and-shape-changes-during-decoding.jpg"/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/LOD-and-shape-changes-during-decoding.jpg"/>
</p>
According to the image above, the only phase that changes the LoD is beam search.

4
doc/fluid/design/others/gan_api.md
Unescape View File

@ -7,14 +7,14 @@ It applies several important concepts in machine learning system design, includi
In our GAN design, we wrap it as a user-friendly easily customized python API to design different models. We take the conditional DC-GAN (Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [https://arxiv.org/abs/1511.06434]) as an example due to its good performance on image generation.
<p align="center">
<img src="./test.dot.png" width = "35%" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/test.dot.png" width = "35%" align="center"/><br/>
Figure 1. The overall running logic of GAN. The black solid arrows indicate the forward pass; the green dashed arrows indicate the backward pass of generator training; the red dashed arrows indicate the backward pass of the discriminator training. The BP pass of the green (red) arrow should only update the parameters in the green (red) boxes. The diamonds indicate the data providers. d\_loss and g\_loss marked in red and green are the two targets we would like to run.
</p>
The operators, layers and functions required/optional to build a GAN demo is summarized in https://github.com/PaddlePaddle/Paddle/issues/4563.
<p align="center">
<img src="./dcgan.png" width = "90%" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/dcgan.png" width = "90%" align="center"/><br/>
Figure 2. Photo borrowed from the original DC-GAN paper.
</p>

2
doc/fluid/dev/releasing_process.md
Unescape View File

@ -37,7 +37,7 @@ PaddlePaddle每次发新的版本，遵循以下流程:
可以在此页面的"Artifacts"下拉框中找到生成的3个二进制文件，分别对应CAPI，`cp27m`和`cp27mu`的版本。然后按照上述的方法
使用`twine`工具上传即可。
<img src="ci_build_whl.png">
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/ci_build_whl.png">
* 注：CI环境使用 https://github.com/PaddlePaddle/buildtools 这里的DockerImage作为编译环境以支持更多的Linux
发型版，如果需要手动编译，也可以使用这些镜像。这些镜像也可以从 https://hub.docker.com/r/paddlepaddle/paddle_manylinux_devel/tags/ 下载得到。

2
doc/fluid/howto/performance/profiler.md
Unescape View File

@ -23,7 +23,7 @@ But how to record the time for the mixed C++ and CUDA program? There many C++ A
The overall flow is shown as the following figure.
<img src="./images/profiler.png" align="center"/><br/>
<img src="https://raw.githubusercontent.com/PaddlePaddle/Paddle/develop/doc/fluid/images/profiler.png" align="center"/><br/>
### Event

56
doc/fluid/images/2_level_rnn.dot
Unescape View File

@ -0,0 +1,56 @@
digraph G {
rnn [label="1st level RNN" shape=box]
subgraph cluster0 {
label = "time step 0"
sent0 [label="sentence"]
sent1 [label="sentence"]
rnn1 [label="2nd level RNN" shape=box]
sent0 -> rnn1
sent1 -> rnn1
}
subgraph cluster1 {
label = "time step 1"
sent2 [label="sentence"]
sent3 [label="sentence"]
rnn2 [label="2nd level RNN" shape=box]
sent2 -> rnn2
sent3 -> rnn2
}
subgraph cluster2 {
label = "time step 2"
sent4 [label="sentence"]
sent5 [label="sentence"]
rnn3 [label="2nd level RNN" shape=box]
sent4 -> rnn3
sent5 -> rnn3
}
para0 [label="paragraph info 0"]
para1 [label="paragraph info 1"]
para2 [label="paragraph info 2"]
rnn1 -> para0
rnn2 -> para1
rnn3 -> para2
para0 -> rnn
para1 -> rnn
para2 -> rnn
chapter [label="chapter info"]
rnn -> chapter
}

BIN
doc/fluid/images/2_level_rnn.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 51 KiB

Some files were not shown because too many files have changed in this diff Show More

Write Preview
Loading…
Cancel
Save