Icon

02_​Text_​Generation_​Fairy_​Tales_​Deployment

Generate Text Using a Many-To-One LSTM Network (Deployment)

This workflows shows two options how the previously trained TensorFlow network to generate fairy tales can be used to generates text in fairy tale style.

Both options read the previously trained TensorFlow network and predict a sequences of index-encoded characters within a loop.

The difference between the two options is in the Extract Index metanode.
The metanode uses probability distribution over all possible indexes to make the predictions. In the Deployment Workflow I the index with the highest probability is extracted. In the Deployment workflow II the next index based is picked based on the given probability distribution.





Deployment Workflow II: Pick next character according to probability distribution Deplyment Workflow I: Next character = character with highest probability Append predicted charseperate inputfrom network outputSplit input collectionSplit input collectionRead modelseperate inputfrom network outputAppend predicted charOutput probabilityfor each characterplus input collectionRead modelOutput probabilityfor each characterplus input collection Extract Index Create Collection RecursiveLoop Start Column Appender(deprecated) ExtractPredicted Text Column Splitter Delete First Charof Input Sequence Split CollectionColumn Recursive Loop End Extract Index Delete First Charof Input Sequence Create Collection Split CollectionColumn TensorFlowNetwork Reader RecursiveLoop Start Recursive Loop End Read andPre-Process ExtractPredicted Text Column Splitter Read andPre-Process RowID Column Appender TensorFlowNetwork Executor TensorFlowNetwork Reader TensorFlowNetwork Executor Deployment Workflow II: Pick next character according to probability distribution Deplyment Workflow I: Next character = character with highest probability Append predicted charseperate inputfrom network outputSplit input collectionSplit input collectionRead modelseperate inputfrom network outputAppend predicted charOutput probabilityfor each characterplus input collectionRead modelOutput probabilityfor each characterplus input collectionExtract Index Create Collection RecursiveLoop Start Column Appender(deprecated) ExtractPredicted Text Column Splitter Delete First Charof Input Sequence Split CollectionColumn Recursive Loop End Extract Index Delete First Charof Input Sequence Create Collection Split CollectionColumn TensorFlowNetwork Reader RecursiveLoop Start Recursive Loop End Read andPre-Process ExtractPredicted Text Column Splitter Read andPre-Process RowID Column Appender TensorFlowNetwork Executor TensorFlowNetwork Reader TensorFlowNetwork Executor

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: kathrinmelcher
Created at: 2018-11-23
On NodePit since: 2022-07-30
Last update: 2024-12-23
Created with KNIME version: v4.3.0
Tags: deep learningkerastext generationRNNLSTMtext analysissequence analysisneural networktext processingNLPNatural Language Processing

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!