@@ -5,7 +5,7 @@ This document describes the RNN (Recurrent Neural Network) operator and how it i
...
@@ -5,7 +5,7 @@ This document describes the RNN (Recurrent Neural Network) operator and how it i
## RNN Algorithm Implementation
## RNN Algorithm Implementation
<palign="center">
<palign="center">
<imgsrc="./images/rnn.jpg"/>
<imgsrc="./rnn.jpg"/>
</p>
</p>
The above diagram shows an RNN unrolled into a full network.
The above diagram shows an RNN unrolled into a full network.
...
@@ -22,7 +22,7 @@ There are several important concepts here:
...
@@ -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.
There could be local variables defined in each step-net. PaddlePaddle runtime realizes these variables in *step-scopes* which are created for each step.
<palign="center">
<palign="center">
<imgsrc="./images/rnn.png"/><br/>
<imgsrc="./rnn.png"/><br/>
Figure 2 illustrates the RNN's data flow
Figure 2 illustrates the RNN's data flow
</p>
</p>
...
@@ -49,7 +49,7 @@ or copy the memory value of the previous step to the current ex-memory variable.
...
@@ -49,7 +49,7 @@ or copy the memory value of the previous step to the current ex-memory variable.
### Usage in Python
### Usage in Python
For more information on Block, please refer to the [design doc](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/block.md).
For more information on Block, please refer to the [design doc](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/fluid/design/concepts/block.md).
We can define an RNN's step-net using a Block:
We can define an RNN's step-net using a Block:
...
@@ -93,7 +93,7 @@ For example, we could have a 2-level RNN, where the top level corresponds to par
...
@@ -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.
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.
<palign="center">
<palign="center">
<imgsrc="./images/2_level_rnn.png"/>
<imgsrc="./2_level_rnn.png"/>
</p>
</p>
```python
```python
...
@@ -149,5 +149,5 @@ If the `output_all_steps` is set to False, it will only output the final time st
...
@@ -149,5 +149,5 @@ If the `output_all_steps` is set to False, it will only output the final time st
...#define the program, cost, and create sgd optimizer
optimize_ops,params_grads=sgd_optimizer.minimize(avg_cost)#get optimize OPs and gradient parameters
t=fluid.DistributeTranspiler()# create the transpiler instance
# slice the program into 2 pieces with optimizer_ops and gradient parameters list, as well as pserver_endpoints, which is a comma separated list of [IP:PORT] and number of trainers
This document provides answers to some of the frequently asked questions about PaddlePaddle. If you have a question that is not covered here, please go to `PaddlePaddle Community <https://github.com/PaddlePaddle/Paddle/issues>`_ , to find an answer or submit new `issue <https://github.com/PaddlePaddle/Paddle/issues/new>`_ , we will reply in time.