Altair RISE

A program to recognize and reward our most engaged community members

Nominate Yourself Now!

how to connect RNN layer to another RNN layer in keras

Hi everyone,

i have been facing this trouble for quite some time and i really hope that i get some reply on this. Is this due to the problem of the keras installation or just that i did not know the proper way of putting them together? thank you guys

Find more posts tagged with

AI Studio

Accepted answers

All comments

sgenzer

tagging @pschlunder

Scott

pschlunder

Hi @dass,

in general you can put one reccurent layer after another. Under the hood, the data shape of a previous layer is passed as the input shape of the current one. But you don't need to handle that yourself, except for the first layer. The input shape of the first layer is set with the "input shape" parameter in the Keras Model Operator. Please check the help text of this operator for information on how to set it.

If you're still facing problems make sure to post your process here. You can use the XML view to get a XML representation of the process that you can copy & paste here.

Hope this helps,

Philipp

dass

Hi @pschlunder,

thank you for the reply, i really appreciate it. Sad to say, the model still displaying error whenever i added another layer to it. When dealing with only 1 layer, the model runs perfectly fine. However, when i add in another layer, the output from the first layer does not match with the input for the second layer. I'm not sure if that is really the case, so i have included the xml process and also the error here as well.

<?xml version="1.0" encoding="UTF-8"?><process version="8.1.003">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="8.1.003" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="8.1.003" expanded="true" height="68" name="Retrieve s&amp;p-500-data" width="90" x="45" y="85">
        <parameter key="repository_entry" value="//Keras Samples/sp_500_regression/s&amp;p-500-data"/>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="8.1.003" expanded="true" height="82" name="Select Attributes" width="90" x="179" y="85">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="Close"/>
        <parameter key="attributes" value="Date|Open|Close"/>
      </operator>
      <operator activated="true" class="normalize" compatibility="8.1.003" expanded="true" height="103" name="Normalize" width="90" x="313" y="85">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="Close"/>
      </operator>
      <operator activated="true" class="series:windowing" compatibility="7.4.000" expanded="true" height="82" name="Windowing" width="90" x="447" y="85">
        <parameter key="window_size" value="30"/>
        <parameter key="label_attribute" value="Close"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="8.1.003" expanded="true" height="82" name="Set Role" width="90" x="581" y="85">
        <parameter key="attribute_name" value="Close-29"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="split_data" compatibility="8.1.003" expanded="true" height="103" name="Split Data" width="90" x="581" y="238">
        <enumeration key="partitions">
          <parameter key="ratio" value="0.9"/>
          <parameter key="ratio" value="0.1"/>
        </enumeration>
        <parameter key="sampling_type" value="linear sampling"/>
      </operator>
      <operator activated="true" class="keras:sequential" compatibility="1.0.003" expanded="true" height="166" name="Keras Model" width="90" x="782" y="136">
        <parameter key="input shape" value="(30,1)"/>
        <parameter key="optimizer" value="Adam"/>
        <parameter key="learning rate" value="0.001"/>
        <enumeration key="metric"/>
        <parameter key="epochs" value="5"/>
        <enumeration key="callbacks">
          <parameter key="callbacks" value="TensorBoard(log_dir='./logs', histogram_freq=0, write_graph=True, write_images=False, embeddings_freq=0, embeddings_layer_names=None, embeddings_metadata=None)"/>
        </enumeration>
        <process expanded="true">
          <operator activated="true" class="keras:core_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Core Layer (2)" width="90" x="648" y="136">
            <parameter key="layer_type" value="Reshape"/>
            <parameter key="target_shape" value="(30,1)"/>
            <parameter key="dims" value="1.1"/>
          </operator>
          <operator activated="true" class="keras:recurrent_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Recurrent Layer" width="90" x="782" y="136">
            <parameter key="no_units" value="8"/>
          </operator>
          <operator activated="true" class="keras:recurrent_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Recurrent Layer (2)" width="90" x="916" y="136">
            <parameter key="no_units" value="8"/>
          </operator>
          <operator activated="true" class="keras:core_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Core Layer" width="90" x="1050" y="136">
            <parameter key="activation_function" value="'linear'"/>
            <parameter key="dims" value="1.1"/>
          </operator>
          <connect from_op="Add Core Layer (2)" from_port="layers 1" to_op="Add Recurrent Layer" to_port="layers"/>
          <connect from_op="Add Recurrent Layer" from_port="layers 1" to_op="Add Recurrent Layer (2)" to_port="layers"/>
          <connect from_op="Add Recurrent Layer (2)" from_port="layers 1" to_op="Add Core Layer" to_port="layers"/>
          <connect from_op="Add Core Layer" from_port="layers 1" to_port="layers 1"/>
          <portSpacing port="sink_layers 1" spacing="0"/>
          <portSpacing port="sink_layers 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="keras:apply" compatibility="1.0.003" expanded="true" height="82" name="Apply Keras Model" width="90" x="849" y="391">
        <parameter key="batch_size" value="128"/>
      </operator>
      <connect from_op="Retrieve s&amp;p-500-data" from_port="output" to_op="Select Attributes" to_port="example set input"/>
      <connect from_op="Select Attributes" from_port="example set output" to_op="Normalize" to_port="example set input"/>
      <connect from_op="Normalize" from_port="example set output" to_op="Windowing" to_port="example set input"/>
      <connect from_op="Windowing" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Split Data" to_port="example set"/>
      <connect from_op="Split Data" from_port="partition 1" to_op="Keras Model" to_port="training set"/>
      <connect from_op="Split Data" from_port="partition 2" to_op="Apply Keras Model" to_port="unlabelled data"/>
      <connect from_op="Keras Model" from_port="model" to_op="Apply Keras Model" to_port="model"/>
      <connect from_op="Apply Keras Model" from_port="labelled data" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

error.PNG

varunm1

@dass did your issue resolved? If so can you provide XML code for the same?