Keras and LSTM configuration problem

ipasha
ipasha New Altair Community Member
edited November 2024 in Community Q&A

I am experiencing problem configuring Keras/LSTM model. I get the following error dueing execution

Execution of Python script failed

Please check your Python script: ValueError:

Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (212, 41) (script, line 295)

 

LayerListIOObject

LSTM(41, input_shape=var_input_shape, batch_input_shape=(1, 2, 17), activation='tanh', recurrent_activation='tanh', use_bias=True, kernel_initializer=glorot_uniform(seed=None), recurrent_initializer=glorot_uniform(seed=None), bias_initializer=Zeros(), unit_forget_bias=True, kernel_regularizer=None,recurrent_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None, bias_constraint=None, dropout=0.0, recurrent_dropout=0.0, stateful=True, unroll=False, implementation=0),

Dense(2, activation='softmax', use_bias=True, kernel_initializer=glorot_uniform(seed=None), bias_initializer=Zeros(), kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)

<?xml version="1.0" encoding="UTF-8"?><process version="8.0.001">

<context>

<input/>

<output/>

<macros/>

</context>

<operator activated="true" class="process" compatibility="8.0.001" expanded="true" name="Process">

<process expanded="true">

<operator activated="true" class="read_excel" compatibility="8.0.001" expanded="true" height="68" name="Read Excel" width="90" x="45" y="34">

<parameter key="excel_file" value="C:\Users\ipasha\.RapidMiner\repositories\Local Repository\TextMining\Data\State.xlsx"/>

<list key="annotations"/>

<list key="data_set_meta_data_information"/>

</operator>

<operator activated="true" class="set_role" compatibility="8.0.001" expanded="true" height="82" name="Set Role" width="90" x="179" y="34">

<parameter key="attribute_name" value="PortState"/>

<parameter key="target_role" value="label"/>

<list key="set_additional_roles">

<parameter key="PortState" value="label"/>

</list>

</operator>

<operator activated="true" class="split_data" compatibility="8.0.001" expanded="true" height="103" name="Split Data" width="90" x="313" y="187">

<enumeration key="partitions">

<parameter key="ratio" value="0.9"/>

<parameter key="ratio" value="0.1"/>

</enumeration>

</operator>

<operator activated="true" class="keras:sequential" compatibility="1.0.003" expanded="true" height="166" name="Keras Model" width="90" x="447" y="34">

<parameter key="input shape" value="(41,)"/>

<parameter key="loss" value="sparse_categorical_crossentropy"/>

<parameter key="optimizer" value="Adam"/>

<enumeration key="metric"/>

<parameter key="epochs" value="128"/>

<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:recurrent_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Recurrent Layer" width="90" x="112" y="34">

<parameter key="layer_type" value="LSTM"/>

<parameter key="no_units" value="41"/>

<parameter key="recurrent_activation" value="tanh"/>

<parameter key="stateful" value="true"/>

</operator>

<operator activated="true" class="keras:core_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Core Layer (2)" width="90" x="447" y="34">

<parameter key="no_units" value="2"/>

<parameter key="activation_function" value="'softmax'"/>

<parameter key="dims" value="1.1"/>

</operator>

<connect from_op="Add Recurrent Layer" from_port="layers 1" to_op="Add Core Layer (2)" to_port="layers"/>

<connect from_op="Add Core Layer (2)" 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="581" y="187"/>

<connect from_op="Read Excel" from_port="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>

　

What configuration change do I need to fix this problem?

 

Thanks

Tagged:

Answers

  • sgenzer
    sgenzer
    Altair Employee

    hello @ipasha - welcome to the community. I'm tagging our Keras guru @jpuente in hopes he has time to respond.

     

    Scott

     

  • ipasha
    ipasha New Altair Community Member

    Thanks Scott. I am still waiting for a response from the Keras guru @jpuente!

  • sgenzer
    sgenzer
    Altair Employee

    @jpuente is a busy guy. It's not easy being a guru. :)

     

    Maybe @jacobcybulski or @dgrzech or @M_Martin or @pschlunder have a moment?

     

    Scott

     

  • pschlunder
    pschlunder New Altair Community Member

    Hi,

     

    you're defining a wrong input_shape. Recurrent layers await (time)steps and the data sets input dimension as an input.

     

    Please checkout the included s&p 500 regression examples of the RapidMiner Keras Operator. It uses Conv Layers but works very similar.

     

    We also have a recorded webinar on using the extension, you can find the recording as well as the slide deck here:

    https://rapidminer.com/resource/state-deep-learning/

     

    Some additional resources to check out:

    https://keras.io/getting-started/sequential-model-guide/#specifying-the-input-shape

    https://keras.io/layers/recurrent/#rnn

     

    Regards,

    Philipp

  • luc_bartkowski
    luc_bartkowski New Altair Community Member

    You might like the following link to a PDF-document that includes all slides from RapidMiner's Philipp Schlunder.

    This PDF includes:

    1. Explanations for all Keras example processes that RapidMiner distributes in their Keras extensions, including settings of the input shape.
    2. The configuration in order to use TensorBoard.

    I couldn't find this PDF on RapidMiners site. Also, the video from Philipp is truncated, it doesn't show the explanation of the examples. I, therefore, found this PDF very useful. 

  • luc_bartkowski
    luc_bartkowski New Altair Community Member

    Philipp Schlunder presentation

  • varunm1
    varunm1 New Altair Community Member

    @pschlunder @luc_bartkowski @jpuente

    Hello,

     

    I am trying to apply Recurrent Network with simple RNN. I am encountering issue with input dimensions. The error states that expected simple_rnn_1 input to have 3 dimensions but got an array of shape (1029,408). I gave input shape of keras model as (1,408) where 1 is the time step and 408 is the number of attributed in my dataset. Batch size is 10. But still I am unable to understand why I am encountering this issue. Your help is much appreciated. Please find XML code below. 

     

    <?xml version="1.0" encoding="UTF-8"?><process version="8.2.000">
    <context>
    <input/>
    <output/>
    <macros/>
    </context>
    <operator activated="true" class="process" compatibility="8.2.000" expanded="true" name="Process">
    <process expanded="true">
    <operator activated="true" class="retrieve" compatibility="8.2.000" expanded="true" height="68" name="Retrieve_2_Clip_ORG_CB_T2" width="90" x="45" y="85">
    <parameter key="repository_entry" value="2_Clip_ORG_CB_T2"/>
    </operator>
    <operator activated="true" class="concurrency:cross_validation" compatibility="8.2.000" expanded="true" height="145" name="Cross Validation" width="90" x="380" y="34">
    <parameter key="number_of_folds" value="5"/>
    <process expanded="true">
    <operator activated="true" class="keras:sequential" compatibility="1.0.003" expanded="true" height="166" name="Keras Model" width="90" x="179" y="34">
    <parameter key="input shape" value="(1,408)"/>
    <parameter key="optimizer" value="Adam"/>
    <enumeration key="metric"/>
    <parameter key="epochs" value="20"/>
    <parameter key="batch size" value="10"/>
    <enumeration key="callbacks"/>
    <process expanded="true">
    <operator activated="true" class="keras:recurrent_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Recurrent Layer" width="90" x="313" y="34">
    <parameter key="no_units" value="200"/>
    <parameter key="activation" value="relu"/>
    <parameter key="dropout" value="0.3"/>
    <parameter key="recurrent_dropout" value="0.3"/>
    </operator>
    <operator activated="true" class="keras:core_layer" compatibility="1.0.003" expanded="true" height="82" name="Add Core Layer" width="90" x="447" y="34">
    <parameter key="no_units" value="2"/>
    <parameter key="activation_function" value="'softmax'"/>
    <parameter key="target_shape" value="2"/>
    <parameter key="dims" value="1.1"/>
    </operator>
    <connect from_op="Add Recurrent Layer" 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>
    <connect from_port="training set" to_op="Keras Model" to_port="training set"/>
    <connect from_op="Keras Model" from_port="model" to_port="model"/>
    <portSpacing port="source_training set" spacing="0"/>
    <portSpacing port="sink_model" spacing="0"/>
    <portSpacing port="sink_through 1" spacing="0"/>
    </process>
    <process expanded="true">
    <operator activated="true" class="keras:apply" compatibility="1.0.003" expanded="true" height="82" name="Apply Keras Model" width="90" x="45" y="34"/>
    <operator activated="true" class="performance" compatibility="8.2.000" expanded="true" height="82" name="Performance" width="90" x="179" y="34"/>
    <connect from_port="model" to_op="Apply Keras Model" to_port="model"/>
    <connect from_port="test set" to_op="Apply Keras Model" to_port="unlabelled data"/>
    <connect from_op="Apply Keras Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
    <connect from_op="Performance" from_port="performance" to_port="performance 1"/>
    <portSpacing port="source_model" spacing="0"/>
    <portSpacing port="source_test set" spacing="0"/>
    <portSpacing port="source_through 1" spacing="0"/>
    <portSpacing port="sink_test set results" spacing="0"/>
    <portSpacing port="sink_performance 1" spacing="0"/>
    <portSpacing port="sink_performance 2" spacing="0"/>
    </process>
    </operator>
    <connect from_op="Retrieve_2_Clip_ORG_CB_T2" from_port="output" to_op="Cross Validation" to_port="example set"/>
    <connect from_op="Cross Validation" from_port="performance 1" 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>

Categories