This node allows custom training and fine-tuning/transfer learning of a (Python compatible) deep learning network in a local Python installation via a user-defined script. The path to the Python executable has to be configured in Preferences → KNIME → Python. It also allows to import Jupyter notebooks as Python modules via the knime_jupyter module that is part of the Python workspace.
Options
Script
Input Ports
- The deep learning network. Referred to as input_network in the Python script. Can be any deep learning network which can be used in Python.
- The input table. Referred to as input_table in the Python script, where it is a pandas.DataFrame.
Output Ports
- The trained output deep learning network. This is the content of the variable output_network which has to be defined in the script and has to be a deep learning network known to KNIME. The network can then be used in common "DL Python" nodes or in nodes which are specific to the network type.
Popular Predecessors
- Column Filter5 %
- Data Explorer5 %
- Excel Reader4 %
Row Filter (deprecated)3 %Python Script (1⇒1)3 %- Keras Dense Layer3 %
- Shuffle3 %
- DL Python Network Learner3 %
Table Reader2 %- Equal Size Sampling2 %
- Table Partitioner2 %
- Rule Engine2 %
- DL Python Network Creator2 %
- DL Python Network Editor2 %
- DL Python Network Executor2 %
- Image Converter2 %
- Data Generator2 %
- Keras Freeze Layers2 %
- Keras Network Learner2 %
- Cell to Model2 %
- Python Script (legacy)2 %
- Normalizer2 %
- Row Sampler2 %
Table Row to Variable1 %Keras Dense Layer1 %- Image to DataRow1 %
- CSV Reader1 %
- Google Sheets Reader1 %
- Split Collection Column< 1 %
Python Script (1⇒2)< 1 %Database Reader< 1 %- SMOTE< 1 %
- String to Number< 1 %
- Double to Integer< 1 %
- Integer Input (legacy)< 1 %
- Scorer< 1 %
- String to Number (PMML)< 1 %
- Create Folder< 1 %
Table Column to Variable< 1 %CSV Reader< 1 %File Reader< 1 %- Table Creator< 1 %
- Java Snippet< 1 %
- Category to Number< 1 %
String To Number< 1 %- Column Resorter< 1 %
- Missing Value< 1 %
Column Rename< 1 %- String Manipulation (Variable)< 1 %
Merge Variables< 1 %- Keras Network Reader< 1 %
- String Input (legacy)< 1 %
- Image Normalizer< 1 %
- Parameter Optimization Loop Start< 1 %
- Python Source (legacy)< 1 %
- Columns to Collection< 1 %
Counting Loop Start< 1 %- X-Partitioner< 1 %
- Concatenate< 1 %
- Expand Bit Vector< 1 %
- Number to String< 1 %
- Column Appender< 1 %
- One to Many< 1 %
Joiner< 1 %Column Splitter< 1 %CASE Switch Model (End)< 1 %DL Network Executor< 1 %- Keras Leaky ReLU Layer< 1 %
Keras Convolution 3D Layer< 1 %- Keras Input Layer< 1 %
- Keras Dot Layer< 1 %
- ONNX to TensorFlow Network Converter< 1 %
- Keras to TensorFlow Network Converter< 1 %
- Vocabulary Extractor (legacy)< 1 %
- Data Row to Image< 1 %
Python Script (2⇒1)< 1 %Python Script (2⇒2)< 1 %- Python Edit Variable (legacy)< 1 %
- String to Date/Time (legacy)< 1 %
- Twitter Users (legacy)< 1 %
- Model Reader< 1 %
Row Splitter (deprecated)< 1 %- RowID< 1 %
- Rule Engine Variable< 1 %
- TensorFlow Network Reader< 1 %
- TensorFlow 2 Network Reader< 1 %
- Model Loop Start< 1 %
Views
- Standard output
- The text sent by Python to the standard output during the execution of this node.
- Error output
- The text sent by Python to the error output during the execution of this node.
Workflows
00_Keras_Transfer_LearningKNIME Hub- 00_Keras_Transfer_LearningKNIME Hub
- 01_BERT_Sentiment_AnalysisKNIME Hub
- 01_BERT_Sentiment_AnalysisKNIME Hub
- 01_Train GAN for Image GenerationKNIME Hub
- Show all 44 workflows
Links
- No links available
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.