NodeDL Python Network Executor

Predictor

This node allows custom execution 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.

Input Ports

  1. Port Type: DLPythonNetworkPortObject
    The trained deep learning network. Referred to as input_network in the Python script. Can be any deep learning network which can be used in Python.
  2. Port Type: Data
    The input table. Referred to as input_table in the Python script, where it is a pandas.DataFrame.

Output Ports

  1. Port Type: Data
    The output table. This is the content of the variable output_table which has to be defined in the script and has to be a pandas.DataFrame in order for this node to execute successfully.

  1. Train simple CNN

    deep learning Keras image classification
    In this workflow we create a simple Convolutional Neural Network using the DL Python Network Creator. We train this netw…
    shima0011 > 04_Analytics > 14_Deep_Learning > 02_Keras > 04_Cats_and_Dogs > 02_Train_simple_CNN

  2. [KNIME Nodes] KN-301 Simple Demand Forecasting Neural Networks

    Neural Networks Deep Learning Sales Forecast
    Compares the Keras Layer Nodes against the DL Python nodes. Builds four models which attempt to predict future sales. Tw…
    scientificstrategy > KNIME Nodes > KN-301 Simple Demand Forecasting Neural Networks v03

  3. WebPortal Predictions

    The workflow reads in a trained VGG16 model from the preceeding workflow, and applies it to a user uploaded image file (…
    knime > Examples > 50_Applications > 31_Histopathology_Blog_Post > _legacy_version > 03_WebPortal_Predictions

  4. Fine-tune VGG16 (Python)

    deep learning Keras image classification
    Instead of creating our own network architecture as in the previous workflow "Train simple CNN", in this workflow we use…
    shima0011 > 04_Analytics > 14_Deep_Learning > 02_Keras > 04_Cats_and_Dogs > 03_Fine-tune_VGG16_Python

  5. Neural Machine Translation English to German

    deep learning keras sequence analysis text analysis text processing machine translation neural machine translation neural language translation lstm encoder decoder neural network sequence to sequence
    Uses a character level encoder-decoder network of LSTMs. The encoder network reads the input sentence character by chara…
    shima0011 > 04_Analytics > 14_Deep_Learning > 02_Keras > 05_Neural_Machine_Translation

  6. Fine-tune VGG16 (Python)

    deep learning Keras image classification
    Instead of creating our own network architecture as in the previous workflow "Train simple CNN", in this workflow we use…
    knime > Examples > 04_Analytics > 14_Deep_Learning > 02_Keras > 04_Cats_and_Dogs > 03_Fine-tune_VGG16_Python

  7. Train simple CNN

    deep learning Keras image classification
    In this workflow we create a simple Convolutional Neural Network using the DL Python Network Creator. We train this netw…
    knime > Examples > 04_Analytics > 14_Deep_Learning > 02_Keras > 04_Cats_and_Dogs > 02_Train_simple_CNN

  8. Neural Machine Translation English to German

    deep learning keras sequence analysis text analysis text processing machine translation neural machine translation neural language translation lstm encoder decoder neural network sequence to sequence NLP Natural Language Processing Python
    Uses a character level encoder-decoder network of LSTMs. The encoder network reads the input sentence character by chara…
    knime > Examples > 04_Analytics > 14_Deep_Learning > 02_Keras > 05_Neural_Machine_Translation