NodeDL Python Network Creator

Source

This node allows custom creation 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.

Output ports

  1. Deep Learning Network Type: DLPythonNetworkPortObject
    The 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.

  1. Train a MLP

    deep learning TensorFlow
    This workflow uses the TensorFlow Python bindings to create and train a multilayer perceptron using the Python API. The …
    aajaradata > 02_PYTHON_Tensorflow_MLP

  2. Image Recognition for Retail Use Case: Data Preparation & Building Convolutional Neural Network (CNN) Workflow

    We used neural networks for the image recognition task. Neural networks are massively parallel adaptive processing struc…
    knime > Examples > 50_Applications > 47_Image_Recognition_for_Retail > 01_Data_Preparation_and_CNN_Training

  3. Train a MLP

    deep learning TensorFlow
    This workflow uses the TensorFlow Python bindings to create and train a multilayer perceptron using the Python API. The …
    aajaradata > iris_PYTHON_Tensorflow_MLP

  4. Train a MLP

    deep learning TensorFlow
    This workflow uses the TensorFlow Python bindings to create and train a multilayer perceptron using the Python API. The …
    aajaradata > Iris_PYTHON_Tensorflow_MLP

  5. Train MNIST classifier

    deep learning TensorFlow image classification
    This workflow trains a simple convolutional neural network (CNN) on the MNIST dataset via TensorFlow.
    shima0011 > 04_Analytics > 14_Deep_Learning > 03_TensorFlow > 03_Train_MNIST_classifier

  6. 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

  7. Read Images and Train VGG

    Life Science Image Analysis Deep Learning Keras
    This workflow reads image patches downloaded and prepared by the previous workflows in the workflow group. It loads the …
    knime > Examples > 50_Applications > 31_Histopathology_Blog_Post > _legacy_version > 02_Read_Images_and_Train_VGG

  8. Semantic Segmentation with Deep Learning in KNIME

    deep learning image processing image analysis computer vision unet neural network segmentation semantic segmentation encoder decoder pixel classification NLP Natural Language Processing Python
    This workflow shows how the new KNIME Keras integration can be used to train and deploy a specialized deep neural networ…
    knime > Examples > 04_Analytics > 14_Deep_Learning > 02_Keras > 06_Semantic_Segmentation

  9. Train MNIST classifier

    deep learning TensorFlow image classification
    This workflow trains a simple convolutional neural network (CNN) on the MNIST dataset via TensorFlow.
    aajaradata > 03_PYTHON-Train_MNIST_classifier

  10. Train a MLP

    deep learning TensorFlow
    This workflow uses the TensorFlow Python bindings to create and train a multilayer perceptron using the Python API. The …
    aajaradata > Iris2_PYTHON_Tensorflow_MLP