Merge branch 'develop' into core_inference_prepare

benchmark/cluster/README.md

@@ -36,11 +36,41 @@
 - Trainer Count: 100
 - Metrics: mini-batch / sec
 
-| Batch Size | 32 | 64 | 128 | 256 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | - | - | - | - |
-| PaddlePaddle v2 | - | - | - | - |
-| TensorFlow | - | - | - | - |
+
+<table>
+<thead>
+<tr>
+<th>Batch Size </th>
+<th> 32</th>
+<th>64</th>
+<th>128 </th>
+<th>256</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td>-</td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2  </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+</tbody>
+</table>
 
 ### Measure the Performance for Different PServer Count
 
@@ -48,11 +78,41 @@
 - Batch Size: 64
 - Metrics: mini-batch / sec
 
-| PServer Count | 10 | 20 | 40 | 60 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | - | - | - | - |
-| PaddlePaddle v2 | - | - | - | - |
-| TensorFlow | - | - | - | - |
+
+<table>
+<thead>
+<tr>
+<th>PServer Count  </th>
+<th>10</th>
+<th>20</th>
+<th>40 </th>
+<th>60</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td>-</td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2  </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+</tr>
+</tbody>
+</table>
 
 ### Measure Parallel Efficiency By Increasing Trainer Count
 
@@ -67,11 +127,69 @@ The parallel efficiency is:
 
 $E = \div(S, N)$
 
-| Trainer Counter | 1 | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
-| -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | - | - | - | - | - | - | - | - | - | - | - |
-| PaddlePaddle v2 | - | - | - | - | - | - | - | - | - | - | - | - |
-| TensorFlow | - | - | - | - | - | - | - | - | - | - | - | - | - |
+<table>
+<thead>
+<tr>
+<th>Trainer Counter  </th>
+<th>1</th>
+<th>10</th>
+<th>20 </th>
+<th>30</th>
+<th>40</th>
+<th>50</th>
+<th>60 </th>
+<th>70</th>
+<th>80</th>
+<th>90</th>
+<th>100 </th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2  </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td>-  </td>
+<td>- </td>
+<td>-  </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+<td>- </td>
+<td>-</td>
+<td>- </td>
+<td>- </td>
+</tr>
+</tbody>
+</table>
+
 
 ## Reproduce the benchmark
 

benchmark/cluster/vgg16/README.md

@@ -16,11 +16,41 @@ Setting environment variable: `MKL_NUM_THREADS=1`.
 
 - Metrics: samples / sec
 
-| Batch Size | 32 | 64 | 128 | 256 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | 15.44 | 16.32 | 16.74 | 16.79 |
-| PaddlePaddle v2 | 15.97 | 17.04 | 17.60 | 17.83 |
-| TensorFlow | 9.09 | 9.10 | 9.24 | 8.66 |
+<table>
+<thead>
+<tr>
+<th>Batch Size </th>
+<th> 32</th>
+<th>64</th>
+<th>128 </th>
+<th>256</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td> 15.44 </td>
+<td> 16.32 </td>
+<td> 16.74 </td>
+<td> 16.79 </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2  </td>
+<td> 15.97 </td>
+<td> 17.04 </td>
+<td> 17.60 </td>
+<td> 17.83 </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td> 9.09 </td>
+<td> 9.10 </td>
+<td> 9.24 </td>
+<td> 8.66 </td>
+</tr>
+</tbody>
+</table>
+
 
 ### Different Batch Size
 
@@ -28,12 +58,40 @@ Setting environment variable: `MKL_NUM_THREADS=1`.
 - Trainer Count: 20
 - Metrics: samples / sec
 
-| Batch Size | 32 | 64 | 128 | 256 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | 190.20 | 222.15 | 247.40 | 258.18 |
-| PaddlePaddle v2 | 170.96 | 233.71 | 256.14 | 329.23 |
-| TensorFlow | - | - | - | - |
-
+<table>
+<thead>
+<tr>
+<th>Batch Size </th>
+<th> 32</th>
+<th>64</th>
+<th>128 </th>
+<th>256</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td> 190.20 </td>
+<td> 222.15 </td>
+<td> 247.40 </td>
+<td> 258.18 </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2  </td>
+<td> 170.96 </td>
+<td> 233.71 </td>
+<td> 256.14 </td>
+<td> 329.23 </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+</tr>
+</tbody>
+</table>
 
 ### Accelerate Rate
 
@@ -41,11 +99,41 @@ Setting environment variable: `MKL_NUM_THREADS=1`.
 - Batch Size: 128
 - Metrics: samples / sec
 
-| Trainer Count | 20 | 40 | 80 | 100 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid | 263.29 (78.64%) | 518.80 (77.47%) | 836.26 (62.44%) | 1019.29 (60.89%) |
-| PaddlePaddle v2 (need more tests) | 326.85 (92.85%) | 534.58 (75.93%) | 853.30 (60.60%) | 1041.99 (59.20%) |
-| TensorFlow | - | - | - | - |
+<table>
+<thead>
+<tr>
+<th>Trainer Count </th>
+<th>20</th>
+<th>40</th>
+<th>80</th>
+<th>100</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid</td>
+<td> 263.29 (78.64%) </td>
+<td> 518.80 (77.47%) </td>
+<td> 836.26 (62.44%) </td>
+<td> 1019.29 (60.89%) </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2 (need more tests)   </td>
+<td> 326.85 (92.85%) </td>
+<td> 534.58 (75.93%) </td>
+<td> 853.30 (60.60%) </td>
+<td> 1041.99 (59.20%) </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+</tr>
+</tbody>
+</table>
+
 
 ### Different Pserver Count
 
@@ -53,11 +141,41 @@ Setting environment variable: `MKL_NUM_THREADS=1`.
 - Batch Size: 128
 - Metrics: samples/ sec
 
-| PServer Count | 3 | 6 |10 | 20 |
-| -- | -- | -- | -- | -- |
-| PaddlePaddle Fluid(should fix in next PR) | 589.1 | 592.6 | 656.4 | 655.8 |
-| PaddlePaddle v2 | 593.4 | 791.3 | 729.7 | 821.7 |
-| TensorFlow | - | - | - | - |
+<table>
+<thead>
+<tr>
+<th>PServer Count </th>
+<th>3</th>
+<th>6</th>
+<th>10</th>
+<th>20</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> PaddlePaddle Fluid(should fix in next PR) </td>
+<td> 589.1 </td>
+<td> 592.6 </td>
+<td> 656.4 </td>
+<td> 655.8 </td>
+</tr>
+<tr>
+<td>PaddlePaddle v2 (need more tests)   </td>
+<td> 593.4 </td>
+<td> 791.3 </td>
+<td> 729.7 </td>
+<td> 821.7 </td>
+</tr>
+<tr>
+<td>TensorFlow </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+<td> - </td>
+</tr>
+</tbody>
+</table>
+
 
 *The performance gap between Fuild and v2 comes from the network interference.*
 

doc/fluid/api/layers.rst

@@ -494,6 +494,12 @@ reshape
 ..  autofunction:: paddle.fluid.layers.reshape
     :noindex:
 
+pad
+---
+
+..  autofunction:: paddle.fluid.layers.pad
+    :noindex:
+
 scale
 -----
 

doc/fluid/design/algorithm/parameter_average.md

@@ -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:
 
-<img src="./images/asgd.gif" align="center"/><br/>
+<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.
 

doc/fluid/design/concepts/README.md

@@ -6,11 +6,33 @@ Here are some initial thoughts. Your comments are welcome!
 
 I think we need only the following few CMake functions to make a project description mean and clean:
 
-| C++ | CUDA C++ | Go |
-|---|---|---|
-| cc_library | nv_library | go_library |
-| cc_binary | nv_binary | go_binary |
-| cc_test | nv_test | go_test |
+<table>
+<thead>
+<tr>
+<th>C++</th>
+<th>CUDA C++</th>
+<th>Go</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>cc_library </td>
+<td>nv_library </td>
+<td>go_library </td>
+</tr>
+<tr>
+<td>cc_binary </td>
+<td>nv_binary </td>
+<td>go_binary </td>
+</tr>
+<tr>
+<td> cc_test </td>
+<td> nv_test </td>
+<td> go_test </td>
+</tr>
+</tbody>
+</table>
+
 
 - The `_library` functions generate  .a files from source code.
 - The `_binary` functions generate executable binary files.

doc/fluid/design/concepts/block.md

@@ -14,11 +14,29 @@ In programming languages, a block is a pair of curly braces that includes local
 
 Blocks work with control flow structures like `if`, `else`, and `for`, which have equivalents in deep learning:
 
-| programming languages | PaddlePaddle          |
-|-----------------------|-----------------------|
-| for, while loop       | RNN, WhileOp          |
-| if, if-else, switch   | IfElseOp, SwitchOp    |
-| sequential execution  | a sequence of layers  |
+<table>
+<thead>
+<tr>
+<th>programming languages</th>
+<th>PaddlePaddle</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>for, while loop </td>
+<td>RNN, WhileOp </td>
+</tr>
+<tr>
+<td>if, if-else, switch </td>
+<td>IfElseOp, SwitchOp </td>
+</tr>
+<tr>
+<td>sequential execution </td>
+<td>a sequence of layers </td>
+</tr>
+</tbody>
+</table>
+
 
 A key difference is that a C++ program describes a one pass computation, whereas a deep learning program describes both the forward and backward passes.
 
@@ -26,12 +44,33 @@ A key difference is that a C++ program describes a one pass computation, whereas
 
 The existence of the backward pass makes the execution of a block of PaddlePaddle different from traditional programs:
 
-| programming languages | PaddlePaddle                    |
-|-----------------------|---------------------------------|
-| stack                 | scope hierarchy                 |
-| stack frame           | scope                           |
-| push at entering block| push at entering block          |
-| pop at leaving block  | destroy when minibatch completes|
+<table>
+<thead>
+<tr>
+<th>programming languages</th>
+<th>PaddlePaddle</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>stack </td>
+<td>scope hierarchy </td>
+</tr>
+<tr>
+<td>stack frame  </td>
+<td>scope </td>
+</tr>
+<tr>
+<td>push at entering block </td>
+<td>push at entering block </td>
+</tr>
+<tr>
+<td>pop at leaving block </td>
+<td>destroy when minibatch completes </td>
+</tr>
+</tbody>
+</table>
+
 
 1. In traditional programs:
 

doc/fluid/design/concepts/functions_operators_layers.md

@@ -86,12 +86,40 @@ def layer.fc(X):
 
 We'd like to have Python bindings to operators in package `paddle.operator`, and Python compositions of operators in package `paddle.layer`.  So we have the following concepts in above illustrative example:
 
-
-| C++ functions/functors | mul          | add          |             |          |
-|------------------------|--------------|--------------|-------------|----------|
-| C++ operator class     | mulOp        | addOp        | FCOp        |          |
-| Python binding         | operator.mul | operator.add | operator.fc |          |
-| Python function        |              |              |             | layer.fc |
+<table>
+<thead>
+<tr>
+<th>C++ functions/functors</th>
+<th>mul</th>
+<th>add</th>
+<th></th>
+<th></th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>C++ operator class </td>
+<td>mulOp</td>
+<td>addOp </td>
+<td>FCOp </td>
+<td></td>
+</tr>
+<tr>
+<td>Python binding  </td>
+<td>operator.mul</td>
+<td> operator.add </td>
+<td>operator.fc </td>
+<td></td>
+</tr>
+<tr>
+<td>Python function   </td>
+<td></td>
+<td></td>
+<td> </td>
+<td>layer.fc</td>
+</tr>
+</tbody>
+</table>
 
 
 This is how we differentiate layer and operators in PaddlePaddle:

doc/fluid/design/concepts/lod_tensor.md

@@ -2,12 +2,38 @@
 
 Like other deep learning systems, PaddlePaddle supports training models from sequence data.  Also, like other systems, PaddlePaddle represent a mini-batch of sequences as a Tensor.  What is different is that PaddlePaddle doesn't require all sequences in a mini-batch to be of the same length. Thus no need for padding zeros.
 
-|                       | TensorFlow | PaddlePaddle |
-|-----------------------|------------|--------------|
-| RNN                   | Support    | Support      |
-| recursive RNN         | Support    | Support      |
-| padding zeros         | Must       | No need      |
-| blob data type        | Tensor     | LoDTensor    |
+<table>
+<thead>
+<tr>
+<th></th>
+<th>TensorFlow</th>
+<th>PaddlePaddle</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>RNN </td>
+<td>Support </td>
+<td>Support </td>
+</tr>
+<tr>
+<td>recursive RNN </td>
+<td>Support </td>
+<td>Support </td>
+</tr>
+<tr>
+<td>padding zeros </td>
+<td> Must </td>
+<td>No need </td>
+</tr>
+<tr>
+<td> blob data type </td>
+<td> Tensor</td>
+<td> LoDTensor </td>
+</tr>
+</tbody>
+</table>
+
 
 PaddlePaddle achieves this flexibility by passing through a new data type, *LoD Tensor*, which is a Tensor attached with segmentation index known as *LoD*, between operators.  The LoD index doesn't only segment a tensor, but also recursively segments sub-sequences.  This document presents the design of LoD and LoDTensor.
 

doc/fluid/design/concepts/var_desc.md

@@ -10,10 +10,27 @@ PaddlePaddle uses proto message to describe compile time program because :
 
 The computation `Program` consists of nested `Blocks`. Each `Block` will consist of data(i.e. `Variable`)  and  `Operations`. The concept to represent them is in the table below.
 
-| |compile time|runtime|
-|---|---|---|
-|Data|VarDesc(proto)|Variable(cpp)|
-|Operation|OpDesc(proto)|Operator(cpp)|
+<table>
+<thead>
+<tr>
+<th></th>
+<th>compile time</th>
+<th>runtime</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Data </td>
+<td>VarDesc(proto) </td>
+<td>Variable(cpp) </td>
+</tr>
+<tr>
+<td>Operation </td>
+<td>OpDesc(proto) </td>
+<td>Operator(cpp) </td>
+</tr>
+</tbody>
+</table>
 
 
 ## Definition of VarType

doc/fluid/design/concurrent/channel.md

@@ -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

doc/fluid/design/concurrent/concurrent_programming.md

@@ -10,12 +10,42 @@ The answer relies on the fact that a `ProgramDesc` is similar to an abstract syn
 
 The following table compares concepts in Fluid and Go
 
-| Go | Fluid |
-|----|-------|
-|user-defined functions | [layers](https://github.com/PaddlePaddle/Paddle/tree/develop/python/paddle/fluid) |
-| control-flow and built-in functions | [intrinsics/operators](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators) |
-| goroutines, channels | [class ThreadPool](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/framework/thread_pool.h) |
-| runtime | [class Executor](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/executor.h) |
+<table>
+<thead>
+<tr>
+<th></th>
+<th>Go</th>
+<th>Fluid</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<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>
+
 
 ## An Example Concurrent Program
 

doc/fluid/design/concurrent/csp.md

@@ -13,14 +13,41 @@ Most DL systems, including TensorFlow, Caffe2, and MxNet, can asynchronously exe
 
 There were many concurrent programming models, implemented in various forms:
 
-| concurrent programming model | implementation |
-|-----|-----|
-| mutex | types and functions in standard libraries |
-| semaphore | types and functions in standard libraries |
-| communicating sequential processes (CSP) | Go programming language |
-| actor model | Erlang programming language |
-| message passing | MPI |
-| bulk synchronous parallel (BSP) | Pregel distributed programming framework |
+<table>
+<thead>
+<tr>
+<th>concurrent programming model</th>
+<th>implementation</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>mutex </td>
+<td>types and functions in standard libraries </td>
+</tr>
+<tr>
+<td>semaphore </td>
+<td> types and functions in standard libraries </td>
+</tr>
+<tr>
+<td> communicating sequential processes (CSP)  </td>
+<td> Go programming language </td>
+</tr>
+<tr>
+<td> actor model  </td>
+<td> Erlang programming language </td>
+</tr>
+<tr>
+<td> message passing  </td>
+<td> MPI </td>
+</tr>
+<tr>
+<td> bulk synchronous parallel (BSP)   </td>
+<td> Pregel distributed programming framework </td>
+</tr>
+</tbody>
+</table>
+
 
 Since Fluid was designed to be a programming language, we would like to implement CSP in Fluid.
 

doc/fluid/design/concurrent/select_op.md

@@ -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

doc/fluid/design/dist_train/distributed_architecture.md

@@ -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

doc/fluid/design/dist_train/multi_cpu.md

@@ -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
 

doc/fluid/design/dist_train/parameter_server.md

@@ -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

doc/fluid/design/dynamic_rnn/rnn.md

@@ -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>

doc/fluid/design/modules/batch_norm_op.md

@@ -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.

doc/fluid/design/modules/python_api.md

@@ -2,12 +2,33 @@
 
 Due to the refactorization of the PaddlePaddle core, we need Python classes to construct corresponding protobuf messages that describe a DL program.
 
-| Python classes | Protobuf messages |
-| --- | --- |
-| Program | ProgramDesc |
-| Block | BlockDesc |
-| Operator | OpDesc |
-| Variable | VarDesc |
+<table>
+<thead>
+<tr>
+<th>Python classes</th>
+<th>Protobuf messages</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Program </td>
+<td>ProgramDesc </td>
+</tr>
+<tr>
+<td>Block  </td>
+<td>BlockDesc </td>
+</tr>
+<tr>
+<td>Operator </td>
+<td>OpDesc </td>
+</tr>
+<tr>
+<td>Variable </td>
+<td>VarDesc </td>
+</tr>
+</tbody>
+</table>
+
 
 Please be aware that these Python classes need to maintain some construction-time information, which are not part of the protobuf messages.
 

doc/fluid/design/modules/regularization.md

@@ -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).
-
-
-
-
-
-    

doc/fluid/design/motivation/fluid.md

@@ -10,11 +10,37 @@ Fluid is the answer.  Fluid is similar to PyTorch and TensorFlow Eager Execution
 
 Deep learning infrastructure is one of the fastest evolving technologies. Within four years, there have already been three generations of technologies invented.
 
-| Existed since | model as sequence of layers | model as graph of operators | No model |
-|--|--|--|--|
-| 2013 | Caffe, Theano, Torch, PaddlePaddle | | |
-| 2015 | | TensorFlow, MxNet, Caffe2, ONNX, n-graph | |
-| 2016 | | | PyTorch, TensorFlow Eager Execution, PaddlePaddle Fluid |
+<table>
+<thead>
+<tr>
+<th>Existed since</th>
+<th>model as sequence of layers</th>
+<th>model as graph of operators</th>
+<th>No model</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>2013 </td>
+<td>Caffe, Theano, Torch, PaddlePaddle </td>
+<td> </td>
+<td> </td>
+</tr>
+<tr>
+<td>2015 </td>
+<td> </td>
+<td>TensorFlow, MxNet, Caffe2, ONNX, n-graph </td>
+<td> </td>
+</tr>
+<tr>
+<td>2016 </td>
+<td> </td>
+<td>   </td>
+<td> PyTorch, TensorFlow Eager Execution, PaddlePaddle Fluid</td>
+</tr>
+</tbody>
+</table>
+
 
 From the above table, we see that the deep learning technology is evolving towards getting rid of the concept of a model.  To understand the reasons behind this direction, a comparison of the *programming paradigms* or the ways to program deep learning applications using these systems, would be helpful. The following section goes over these.
 

doc/fluid/design/motivation/refactorization.md

@@ -36,11 +36,37 @@ At compile time, the Python program generates a protobuf message representation
 
 At runtime, the C++ program realizes the graph and runs it.
 
-| | Representation (protobuf messages) | Realization (C++ class objects) |
-|---|---|---|
-|Data|[VarDesc](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto#L107)|[Variable](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/variable.h#L24)|
-|Operation|[OpDesc](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto#L35)|[Operator](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/operator.h#L64)|
-|Block|BlockDesc|Block|
+<table>
+<thead>
+<tr>
+<th></th>
+<th>Representation (protobuf messages)</th>
+<th>Realization (C++ class objects) </th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Data</td>
+<td>
+<a href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto#L107">VarDesc</a></td>
+<td>
+<a href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/variable.h#L24">Variable</a></td>
+</tr>
+<tr>
+<td>Operation </td>
+<td>
+<a href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto#L35">OpDesc</a></td>
+<td>
+<a href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/operator.h#L64">Operator</a></td>
+</tr>
+<tr>
+<td>Block </td>
+<td>BlockDesc </td>
+<td>Block </td>
+
+</tbody>
+</table>
+
 
 The word *graph* is interchangeable with *block* in this document.  A graph consists of computation steps and local variables similar to a C++/Java program block, or a pair of parentheses(`{` and `}`).
 

doc/fluid/design/network/deep_speech_2.md

@@ -68,11 +68,33 @@ We roughly break down the project into 14 tasks:
 
 Tasks parallelizable within phases:
 
-Roadmap     | Description                               | Parallelizable Tasks 
------------ | :------------------------------------     | :--------------------
-Phase I	    | Simplified model & components             | *Task 1* ~ *Task 8*
-Phase II    | Standard model & benchmarking & profiling | *Task 9* ~ *Task 12*
-Phase III   | Documentations                            | *Task13* ~ *Task14*
+<table>
+<thead>
+<tr>
+<th>Roadmap</th>
+<th>Description</th>
+<th> Parallelizable Tasks</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Phase I </td>
+<td>Simplified model & components </td>
+<td>Task 1 ~ Task 8</td>
+</tr>
+<tr>
+<td>Phase II </td>
+<td> Standard model & benchmarking & profiling</td>
+<td>Task 9 ~ Task 12 </td>
+</tr>
+<tr>
+<td>Phase III </td>
+<td> Documentations</td>
+<td> Task13 ~ Task14 </td>
+</tr>
+</tbody>
+</table>
+
 
 Issue for each task will be created later. Contributions, discussions and comments are all highly appreciated and welcomed!
 
@@ -94,7 +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>
 
@@ -121,18 +143,63 @@ Key ingredients about the layers:
    - Added to all above layers (except for data and loss layer).
    - Sequence-wise normalization for RNNs: BatchNorm only performed on input-state projection and not state-state projection, for efficiency consideration.
 
+<table>
+<thead>
+<tr>
+<th>Required Components</th>
+<th> PaddlePaddle Support</th>
+<th> Need to Develop</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Data Layer I (Spectrogram) </td>
+<td>Not supported yet.</td>
+<td>TBD (Task 3)</td>
+</tr>
+<tr>
+<td>Data Layer II (Transcription)  </td>
+<td> paddle.data_type.integer_value_sequence</td>
+<td> - </td>
+</tr>
+<tr>
+<td>2D Convolution Layer </td>
+<td> paddle.layer.image_conv_layer</td>
+<td> - </td>
+</tr>
+<tr>
+<td>DataType Converter (vec2seq)</td>
+<td> paddle.layer.block_expand</td>
+<td> - </td>
+</tr>
+<tr>
+<td>Bi-/Uni-directional RNNs </td>
+<td>paddle.layer.recurrent_group</td>
+<td> - </td>
+</tr>
+<tr>
+<td>Row Convolution Layer </td>
+<td>Not supported yet.</td>
+<td>TBD (Task 4)</td>
+</tr>
+<tr>
+<td>CTC-loss Layer </td>
+<td>paddle.layer.warp_ctc</td>
+<td> - </td>
+</tr>
+<tr>
+<td>Batch Normalization Layer </td>
+<td>paddle.layer.batch_norm</td>
+<td> - </td>
+</tr>
+<tr>
+<td>CTC-Beam search </td>
+<td>Not supported yet.</td>
+<td> TBD (Task 6) </td>
+</tr>
+</tbody>
+</table>
 
-Required Components                     | PaddlePaddle Support                      | Need to Develop
-:-------------------------------------  | :--------------------------------------   | :-----------------------
-Data Layer I (Spectrogram)	            | Not supported yet.                        |  TBD (Task 3)
-Data Layer II (Transcription)           | `paddle.data_type.integer_value_sequence` | -
-2D Convolution Layer                    | `paddle.layer.image_conv_layer`           | -
-DataType Converter (vec2seq)            | `paddle.layer.block_expand`               | -
-Bi-/Uni-directional RNNs                | `paddle.layer.recurrent_group`            | -
-Row Convolution Layer                   | Not supported yet.                        | TBD (Task 4)
-CTC-loss Layer                          | `paddle.layer.warp_ctc`                   | -
-Batch Normalization Layer               | `paddle.layer.batch_norm`                 | -
-CTC-Beam search                         | Not supported yet.                        | TBD (Task 6)
 
 ### Row Convolution
 
@@ -141,7 +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>
 

doc/fluid/design/network/sequence_decoder.md

@@ -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.

doc/fluid/design/others/gan_api.md

@@ -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>
 

doc/fluid/dev/index_cn.rst

@@ -4,9 +4,9 @@
 .. toctree::
   :maxdepth: 1
 
-  new_op_en.md
-  new_op_kernel_en.md
-  use_eigen_en.md
+  new_op_cn.md
+  new_op_kernel.md
+  use_eigen_cn.md
   name_convention.md
   support_new_device.md
   releasing_process.md

doc/fluid/dev/index_en.rst

@@ -5,7 +5,7 @@ Development
   :maxdepth: 1
 
   new_op_en.md
-  new_op_kernel_en.md
+  new_op_kernel.md
   use_eigen_en.md
   name_convention.md
   support_new_device.md

doc/fluid/dev/new_op_cn.md

@@ -26,13 +26,32 @@
 
 依据是否包含kernel，可以将Op分为两种：包含Kernel的Op和不包含kernel的Op，前者Op的定义继承自`OperatorWithKernel`，后者继承自`OperatorBase`。本教程主要介绍带Kernel的Op如何写，简单总结Op需要包含的内容如下：
 
-
- 内容            | 定义位置
---------------  | :----------------------
-OpProtoMake定义  | `.cc`文件，Backward Op不需要定义OpProtoMake
-Op定义           | `.cc`文件
-Kernel实现       | CPU、CUDA共享Kernel实现在`.h`文件中，否则，CPU 实现在`.cc`文件中，CUDA 实现在`.cu`文件中。
-注册Op           | Op注册实现在`.cc`文件；Kernel注册CPU实现在`.cc`文件中，CUDA实现在`.cu`文件中
+<table>
+<thead>
+<tr>
+<th>内容</th>
+<th>定义位置</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>OpProtoMake定义 </td>
+<td>`.cc`文件，Backward Op不需要定义OpProtoMake </td>
+</tr>
+<tr>
+<td>Op定义 </td>
+<td> `.cc`文件</td>
+</tr>
+<tr>
+<td>Kernel实现 </td>
+<td> CPU、CUDA共享Kernel实现在`.h`文件中，否则，CPU 实现在`.cc`文件中，CUDA 实现在`.cu`文件中。</td>
+</tr>
+<tr>
+<td>注册Op </td>
+<td> Op注册实现在`.cc`文件；Kernel注册CPU实现在`.cc`文件中，CUDA实现在`.cu`文件中</td>
+</tr>
+</tbody>
+</table>
 
 
 实现新的op都添加至目录[paddle/operators](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators)下，文件命名以`*_op.h`（如有） 、 `*_op.cc` 、`*_op.cu`（如有）结尾。**系统会根据文件名自动构建op和其对应的Python扩展。**

doc/fluid/dev/new_op_en.md

@@ -33,6 +33,33 @@ Op definition           | `.cc` files
 Kernel implementation       | The kernel methods shared between CPU and CUDA are defined in `.h` files. CPU-specific kernels live in `.cc` files, while CUDA-specific kernels are implemented in `.cu`files.
 Registering the Op           | Ops are registered in `.cc` files; For Kernel registration, `.cc` files contain the CPU implementation, while `.cu` files contain the CUDA implementation.
 
+<table>
+<thead>
+<tr>
+<th>Information</th>
+<th> Where is it defined</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>OpProtoMake definition </td>
+<td> `.cc`files, Backward Op does not need an OpProtoMake interface. </td>
+</tr>
+<tr>
+<td>Op definition  </td>
+<td> `.cc` files</td>
+</tr>
+<tr>
+<td>Kernel implementation  </td>
+<td> The kernel methods shared between CPU and CUDA are defined in `.h` files. CPU-specific kernels live in `.cc` files, while CUDA-specific kernels are implemented in `.cu`files.</td>
+</tr>
+<tr>
+<td>Registering the Op  </td>
+<td> Ops are registered in `.cc` files; For Kernel registration, `.cc` files contain the CPU implementation, while `.cu` files contain the CUDA implementation.</td>
+</tr>
+</tbody>
+</table>
+
 
 New Operator implementations are added to the list [paddle/operators](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators), with file names in the format `*_op.h` (if applicable), `*_op.cc`, `*_op.cu` (if applicable).** The system will use the naming scheme to automatically build operators and their corresponding Python extensions.**
 

doc/fluid/dev/releasing_process.md

@@ -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。
@@ -78,13 +78,116 @@ PaddlePaddle开发过程使用[git-flow](http://nvie.com/posts/a-successful-git-
 
 PaddlePaddle每次发版本首先要保证PaddlePaddle Book中所有章节功能的正确性。功能的正确性包括验证PaddlePaddle目前的`paddle_trainer`训练和纯使用`Python`训练模型正确性。
 
-| | 新手入门章节 | 识别数字 | 图像分类 | 词向量 | 情感分析 | 语意角色标注 | 机器翻译 | 个性化推荐 |
-| --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| API.V2 + Docker + GPU  |  |  |  |  |  |  |  |  |
-| API.V2 + Docker + CPU  |  |  |  |  |  |  |  |  |
-| `paddle_trainer` + Docker + GPU |  |  |  |  |  |  |  |  |
-| `paddle_trainer` + Docker + CPU |  |  |  |  |  |  |  |  |
-| API.V2 + Ubuntu + GPU |  |  |  |  |  |  |  |  |
-| API.V2 + Ubuntu + CPU |  |  |  |  |  |  |  |  |
-| `paddle_trainer` + Ubuntu + GPU |  |  |  |  |  |  |  |  |
-| `paddle_trainer` + Ubuntu + CPU |  |  |  |  |  |  |  |  |
+<table>
+<thead>
+<tr>
+<th></th>
+<th>新手入门章节 </th>
+<th> 识别数字</th>
+<th> 图像分类</th>
+<th>词向量</th>
+<th> 情感分析</th>
+<th>语意角色标注</th>
+<th> 机器翻译</th>
+<th>个性化推荐</th>
+</tr>
+</thead>
+
+<tbody>
+<tr>
+<td>API.V2 + Docker + GPU </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td> API.V2 + Docker + CPU </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td>`paddle_trainer` + Docker + GPU </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td>`paddle_trainer` + Docker + CPU </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td> API.V2 + Ubuntu + GPU</td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td>API.V2 + Ubuntu + CPU </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td> `paddle_trainer` + Ubuntu + GPU</td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+
+<tr>
+<td> `paddle_trainer` + Ubuntu + CPU</td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+<td>  </td>
+<td> </td>
+</tr>
+</tbody>
+</table>

doc/fluid/getstarted/concepts/save_model/model_format.md

@@ -16,18 +16,58 @@ As a result, we design a particular format for tensor serialization. By default,
 
 The table below shows a tensor's byte view in detail. Note that all the signed values are written in the little-endian format.
 
-|field name  | type | description |
-| --- | --- | --- |
-| version | uint32_t | Version of saved file. Always 0 now. |
-| tensor desc length | uint32_t | TensorDesc(Protobuf message) length in bytes. |
-| tensor desc | void* | TensorDesc protobuf binary message |
-| tensor data | void* | Tensor's data in binary format. The length of `tensor_data` is decided by `TensorDesc.dims()` and `TensorDesc.data_type()` |
-| lod_level | uint64_t | Level of LoD |
-| length of lod[0] | uint64_t | [Optional] length of lod[0] in bytes. |
-| data of lod[0] | uint64_t*  | [Optional] lod[0].data() |
-| ... | ... | ... |
-
+<table>
+<thead>
+<tr>
+<th>field name</th>
+<th>type </th>
+<th>description </th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> version</td>
+<td> uint32_t </td>
+<td> Version of saved file. Always 0 now.</td>
+</tr>
 
+<tr>
+<td> tensor desc length  </td>
+<td> uint32_t </td>
+<td> TensorDesc(Protobuf message) length in bytes. </td>
+</tr>
+<tr>
+<td>tensor desc </td>
+<td> void*</td>
+<td> TensorDesc protobuf binary message </td>
+</tr>
+<tr>
+<td> tensor data </td>
+<td> void* </td>
+<td> Tensor's data in binary format. The length of `tensor_data` is decided by `TensorDesc.dims()` and `TensorDesc.data_type()` </td>
+</tr>
+<tr>
+<td> lod_level</td>
+<td> uint64_t </td>
+<td> Level of LoD </td>
+</tr>
+<tr>
+<td> length of lod[0] </td>
+<td> uint64_t </td>
+<td> [Optional] length of lod[0] in bytes. </td>
+</tr>
+<tr>
+<td> data of lod[0] </td>
+<td> uint64_t*   </td>
+<td> [Optional] lod[0].data() </td>
+</tr>
+<tr>
+<td>... </td>
+<td> ... </td>
+<td> ... </td>
+</tr>
+</tbody>
+</table>
 
 ## Summary
 

doc/fluid/howto/cluster/fluid_cluster_train_cn.md

@@ -99,13 +99,49 @@ for pass_id in range(100):
 ### 分布式训练脚本运行说明
 分布式任务的运行需要将表格中说明的多个参数进行赋值:
 
-| 参数名 | 值类型 | 说明 | 示例 |
-|:-------------|:------|:---------------------------------------|:-------------|
-| trainer_id | int | 当前训练节点的ID，训练节点ID编号为0 - n-1， n为trainers的值 | 0/1/2/3 |
-| pservers | str | parameter server 列表 | 127.0.0.1:6710,127.0.0.1:6711 |
-| trainers | int | 训练节点的总个数，>0的数字 | 4 |
-| server_endpoint | str | 当前所起的服务节点的IP:PORT | 127.0.0.1:8789 |
-| training_role | str | 节点角色， TRAINER/PSERVER | PSERVER |
+<table>
+<thead>
+<tr>
+<th>参数名</th>
+<th> 值类型</th>
+<th>说明</th>
+<th> 示例</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>trainer_id </td>
+<td> int</td>
+<td> 当前训练节点的ID，训练节点ID编号为0 - n-1， n为trainers的值 </td>
+<td> 0/1/2/3  </td>
+</tr>
+<tr>
+<td>pservers </td>
+<td> str</td>
+<td> parameter server 列表 </td>
+<td> 127.0.0.1:6710,127.0.0.1:6711 </td>
+</tr>
+<tr>
+<td>trainers </td>
+<td>int </td>
+<td> 训练节点的总个数，>0的数字 </td>
+<td> 4 </td>
+</tr>
+<tr>
+<td> server_endpoint</td>
+<td> str </td>
+<td> 当前所起的服务节点的IP:PORT </td>
+<td> 127.0.0.1:8789 </td>
+</tr>
+<tr>
+<td> training_role</td>
+<td>str </td>
+<td> 节点角色， TRAINER/PSERVER </td>
+<td> PSERVER </td>
+</tr>
+</tbody>
+</table>
+
 
 **注意：** ```training_role```是用来区分当前所起服务的角色的，用于训练程序中，用户可根据需要自行定义，其他参数为fluid.DistributeTranspiler的transpile函数所需要，需要在调用函数前进行定义，样例如下：
 

doc/fluid/howto/optimization/cpu_profiling_cn.md

@@ -42,14 +42,40 @@ cprofilev -a 0.0.0.0 -p 3214 -f profile.out main.py
 
 每一列的含义是:
 
-| 列名 | 含义 |
-| --- | --- |
-| ncalls | 函数的调用次数 |
-| tottime | 函数实际使用的总时间。该时间去除掉本函数调用其他函数的时间 |
-| percall | tottime的每次调用平均时间 |
-| cumtime | 函数总时间。包含这个函数调用其他函数的时间 |
-| percall | cumtime的每次调用平均时间 |
-| filename:lineno(function) | 文件名, 行号，函数名 |
+<table>
+<thead>
+<tr>
+<th>列名</th>
+<th>含义 </th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> ncalls</td>
+<td> 函数的调用次数</td>
+</tr>
+<tr>
+<td>tottime</td>
+<td> 函数实际使用的总时间。该时间去除掉本函数调用其他函数的时间</td>
+</tr>
+<tr>
+<td> percall </td>
+<td> tottime的每次调用平均时间</td>
+</tr>
+<tr>
+<td> cumtime</td>
+<td> 函数总时间。包含这个函数调用其他函数的时间</td>
+</tr>
+<tr>
+<td> percall</td>
+<td> cumtime的每次调用平均时间</td>
+</tr>
+<tr>
+<td> filename:lineno(function) </td>
+<td> 文件名, 行号，函数名 </td>
+</tr>
+</tbody>
+</table>
 
 
 ### 寻找性能瓶颈

doc/fluid/howto/optimization/cpu_profiling_en.md

@@ -57,14 +57,40 @@ port, we will see the output like the following:
 where each line corresponds to Python function, and the meaning of
 each column is as follows:
 
-| column | meaning |
-| --- | --- |
-| ncalls | the number of calls into a function |
-| tottime | the total execution time of the function, not including the execution time of other functions called by the function |
-| percall | tottime divided by ncalls |
-| cumtime | the total execution time of the function, including the execution time of other functions being called |
-| percall | cumtime divided by ncalls |
-| filename:lineno(function) | where the function is defined |
+<table>
+<thead>
+<tr>
+<th>column</th>
+<th>meaning </th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td> ncalls</td>
+<td> the number of calls into a function</td>
+</tr>
+<tr>
+<td>tottime</td>
+<td> the total execution time of the function, not including the execution time of other functions called by the function</td>
+</tr>
+<tr>
+<td> percall </td>
+<td> tottime divided by ncalls</td>
+</tr>
+<tr>
+<td> cumtime</td>
+<td> the total execution time of the function, including the execution time of other functions being called</td>
+</tr>
+<tr>
+<td> percall</td>
+<td> cumtime divided by ncalls</td>
+</tr>
+<tr>
+<td> filename:lineno(function) </td>
+<td> where the function is define </td>
+</tr>
+</tbody>
+</table>
 
 ### Identify Performance Bottlenecks
 

doc/fluid/howto/performance/profiler.md

@@ -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
 

doc/fluid/images/2_level_rnn.dot

+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
+}

doc/fluid/images/batch_norm_fork.dot

+digraph ImageBatchNormForkGragh {
+  subgraph cluster_before {
+    Prev [label="...", shape=plaintext];
+    Rnn [label="rnn_op", shape=box];
+    BatchNorm [label="batch_norm_op", shape=box];
+    Fc [label="fc_op", shape=box];
+    After [label="...", shape=plaintext];
+    Prev -> Rnn -> BatchNorm -> Fc -> After;
+    label="original";
+  }
+
+  subgraph cluster_after {
+    Prev2 [label="...", shape=plaintext];
+    Rnn2 [label="rnn_op", shape=box];
+    BatchNorm2_1 [label="train_batch_norm_op", shape=box];
+    BatchNorm2_2 [label="infer_batch_norm_op", shape=box];
+    Fc2_1 [label="fc_op", shape=box];
+    Fc2_2 [label="fc_op", shape=box];
+    After2_1 [label="...", shape=plaintext];
+    After2_2 [label="...", shape=plaintext];
+    Prev2 -> Rnn2 -> BatchNorm2_1 -> Fc2_1 -> After2_1;
+    Rnn2 -> BatchNorm2_2 ->Fc2_2 ->After2_2
+    label="forked";
+  }
+}

doc/fluid/images/graph_construction_example.bash

+cat ./graph_construction_example.dot | \
+    sed 's/color=red/color=red, style=invis/g' | \
+    sed 's/color=green/color=green, style=invis/g' | \
+    dot -Tpng > graph_construction_example_forward_only.png
+
+cat ./graph_construction_example.dot | \
+    sed 's/color=green/color=green, style=invis/g' | \
+    dot -Tpng > graph_construction_example_forward_backward.png
+
+cat ./graph_construction_example.dot | \
+    dot -Tpng > graph_construction_example_all.png

doc/fluid/images/graph_construction_example.dot

+digraph ImageClassificationGraph {
+        ///////// The forward part /////////
+        FeedX [label="Feed", color=blue, shape=box];
+        FeedY [label="Feed", color=blue, shape=box];
+        InitW [label="Init", color=blue, shape=diamond];
+        Initb [label="Init", color=blue, shape=diamond];
+        FC [label="FC", color=blue, shape=box];
+        MSE [label="MSE", color=blue, shape=box];
+
+        x [label="x", color=blue, shape=oval];
+        l [label="l", color=blue, shape=oval];
+        y [label="y", color=blue, shape=oval];
+        W [label="W", color=blue, shape=doublecircle];
+        b [label="b", color=blue, shape=doublecircle];
+        cost [label="cost", color=blue, shape=oval];
+
+        FeedX -> x -> FC -> y -> MSE -> cost [color=blue];
+        FeedY -> l [color=blue];
+        InitW -> W [color=blue];
+        Initb -> b [color=blue];
+        W -> FC [color=blue];
+        b -> FC [color=blue];
+        l -> MSE [color=blue];
+
+        ////////// The backward part /////////
+        MSE_Grad [label="MSE_grad", color=red, shape=box];
+        FC_Grad [label="FC_grad", color=red, shape=box];
+
+        d_cost [label="d cost", color=red, shape=oval];
+        d_y [label="d y", color=red, shape=oval];
+        d_b [label="d b", color=red, shape=oval];
+        d_W [label="d W", color=red, shape=oval];
+
+        cost -> MSE_Grad [color=red];
+        d_cost -> MSE_Grad [color=red];
+        l -> MSE_Grad [color=red];
+        y -> MSE_Grad -> d_y [color=red];
+
+        x -> FC_Grad [color=red];
+        y -> FC_Grad [color=red];
+        d_y -> FC_Grad [color=red];
+        W -> FC_Grad -> d_W [color=red];
+        b -> FC_Grad -> d_b [color=red];
+
+        ////////// The optimizaiton part //////////
+
+        OPT_W [label="SGD", color=green, shape=box];
+        OPT_b [label="SGD", color=green, shape=box];
+
+        W -> OPT_W [color=green];
+        b -> OPT_b [color=green];
+        d_W -> OPT_W -> W [color=green];
+        d_b -> OPT_b -> b [color=green];
+
+        ////////// Groupings //////////
+
+        subgraph clusterMSE {
+                style=invis;
+                MSE;
+                MSE_Grad;
+        }
+
+        subgraph clusterFC {
+                style=invis;
+                FC;
+                FC_Grad;
+        }
+}

doc/fluid/images/rnn.dot

+digraph G {
+  label = "simple RNN implementation" 
+
+  ranksep=2;
+
+  //graph [nodesep=1, ranksep=1];
+
+  node[nodesep=1]
+
+  subgraph cluster0 {
+    label = "global scope"
+    rankdir = TB
+    W
+    boot_memory
+    input
+    output
+  }
+
+  subgraph cluster1 {
+    label = "step-scope 0"
+    rankdir = TB
+    memory0[label="memory"]
+    prememory0[label="pre-memory"]
+    step_input0[label="step input"]
+    step_output0[label="step output"]
+  }
+
+  subgraph cluster2 {
+    label = "step-scope 1"
+    rankdir = TB
+    memory1[label="memory"]
+    prememory1[label="pre-memory"]
+    step_input1[label="step input"]
+    step_output1[label="step output"]
+  }
+
+  subgraph cluster3 {
+    label = "step-scope 2"
+    rankdir = TB
+    memory2[label="memory"]
+    prememory2[label="pre-memory"]
+    step_input2[label="step input"]
+    step_output2[label="step output"]
+  }
+
+  stepnet [shape=box]
+  stepnet0 [shape=box, style=dashed]
+  stepnet1 [shape=box, style=dashed]
+  stepnet2 [shape=box, style=dashed]
+
+
+  edge[color=blue]
+  boot_memory -> prememory0 [label="init" color="blue"]
+  memory0 -> prememory1  [label="copy/reference" color="blue"]
+  memory1 -> prememory2 [label="copy/reference" color="blue"]
+
+  edge[color=black]
+  W -> stepnet0[constraint=false, style=dashed]
+  W -> stepnet1[constraint=false, style=dashed]
+  W -> stepnet2[constraint=false, style=dashed]
+
+  memory0 -> stepnet0[style=dashed]
+  prememory0 -> stepnet0 -> step_output0[style=dashed]
+
+  memory1 -> stepnet1[style=dashed]
+  prememory1 -> stepnet1 -> step_output1[style=dashed]
+
+  memory2 -> stepnet2[style=dashed]
+  prememory2 -> stepnet2 -> step_output2[style=dashed]
+
+  input -> step_input0
+  input -> step_input1
+  input -> step_input2
+
+  step_input0 -> stepnet0 [style=dashed]
+  step_input1 -> stepnet1[style=dashed]
+  step_input2 -> stepnet2[style=dashed]
+
+  step_output0 -> output
+  step_output1 -> output
+  step_output2 -> output
+
+  stepnet0 -> stepnet[style=dashed]
+  stepnet1 -> stepnet[style=dashed]
+  stepnet2 -> stepnet[style=dashed]
+
+}

doc/fluid/images/rnn_2level_data.dot

+digraph G {
+  chapter [label="chapter"]
+
+  subgraph cluster0 {
+    label = "paragraph 0"
+
+    top_rnn0[label="top rnn step 0" shape=box]
+
+    p0 [label="paragraph 0"]
+    p1 [label="paragraph 1"]
+  }
+
+  subgraph cluster1{
+    label = "paragraph 1"
+
+    top_rnn1[label="top rnn step 1" shape=box]
+
+    p2 [label="paragraph 0"]
+    p3 [label="paragraph 1"]
+  }
+
+  subgraph cluster_p0 {
+    label = "sentence 0"
+
+    low_rnn0 [label="low rnn step 0" shape=box]
+    s00 [label="sentence 0"]
+    s01 [label="sentence 1"]
+
+    low_rnn0 -> s00
+    low_rnn0 -> s01
+  }
+
+  subgraph cluster_p1 {
+    label = "sentence 1"
+    low_rnn1 [label="low rnn step 1" shape=box]
+    s10 [label="sentence 0"]
+    s11 [label="sentence 1"]
+    low_rnn1 -> s10
+    low_rnn1 -> s11
+  }
+
+  subgraph cluster_p2 {
+    label = "sentence 1"
+    low_rnn2 [label="low rnn step 0" shape=box]
+    s20 [label="sentence 0"]
+    s21 [label="sentence 1"]
+    low_rnn2 -> s20
+    low_rnn2 -> s21
+  }
+
+  subgraph cluster_p3 {
+    label = "sentence 1"
+    low_rnn3 [label="low rnn step 1" shape=box]
+    s30 [label="sentence 0"]
+    s31 [label="sentence 1"]
+    low_rnn3 -> s30
+    low_rnn3 -> s31
+  }
+
+
+  chapter -> top_rnn0
+  chapter -> top_rnn1
+
+  top_rnn0 -> p0
+  top_rnn0 -> p1
+  top_rnn1 -> p2
+  top_rnn1 -> p3
+
+
+  p0 -> low_rnn0
+  p1 -> low_rnn1
+  p2 -> low_rnn2
+  p3 -> low_rnn3
+
+}

doc/fluid/images/test.dot

+
+digraph Test {
+    z -> generator -> G_img;
+    G_img -> discriminator -> D_f -> d_loss_f;
+    label0 -> d_loss_f -> d_loss;
+
+    img -> discriminator -> D_t -> d_loss_t;
+    label1 -> d_loss_t -> d_loss;
+
+    d_loss -> d_loss_t[color=red, style=dashed];
+    d_loss -> d_loss_f[color=red, style=dashed];
+    d_loss_t -> D_t[color=red, style=dashed];
+    d_loss_f -> D_f[color=red, style=dashed];
+    D_t -> discriminator[color=red, style=dashed];
+    D_f -> discriminator[color=red, style=dashed];
+
+    D_f -> g_loss;
+    label2 -> g_loss;
+
+    g_loss -> D_f[color=green, style=dashed];
+    D_f -> discriminator[color=green, style=dashed];
+    discriminator -> G_img[color=green, style=dashed];
+    G_img -> generator[color=green, style=dashed];
+
+    discriminator [color=red, shape=box];
+    generator [color=green, shape=box];
+    z [shape=diamond];
+    img [shape=diamond];
+    label0 [shape=diamond];
+    label1 [shape=diamond];
+    label2 [shape=diamond];
+
+    d_loss [color=red];
+    g_loss [color=green];
+}