Icon

02_​Train_​simple_​CNN

Train simple CNN

In this workflow we create a simple Convolutional Neural Network using the DL Python Network Creator. We train this network on our image data using the DL Python Network Learner and finally score it using the DL Python Network Executor. The DL Python Network Learner and Executor can be used to write custom training and execution code using Python.

Please note: The workflow series is heavily inspired by the great blog-post of François Chollet (see https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html.)

1. Workflow 01 Preprocess image data

2. Workflow 02 Train simple CNN: In this workflow we create a simple Convolutional Neural Network using the DL Python Network Creator. We train this network on our image data using the DL Python Network Learner and finally score it using the DL Python Network Executor. The DL Python Network Learner and Executor can be used to write custom training and execution code using Python.

3. Workflow 03 Fine-tune VGG16 Python
4. Workflow 04 Fine-tune VGG16

In order to run the example, please make sure you have the following KNIME extensions installed:

* KNIME Deep Learning - Keras Integration (Labs)
* KNIME Image Processing (Community Contributions Trusted)
* KNIME Image Processing - Deep Learning Extension (Community Contributions Trusted)
* KNIME Image Processing - Python Extension (Community Contributions Trusted)
* KNIME Streaming Execution (Labs)

You also need a local Python installation that includes Keras. Please refer to https://www.knime.com/deeplearning#keras for installation recommendations and further information.

KNIME Deep Learning - Classify Cats and Dogs In this series of workflows we want to demonstrate how to solve animage classification problem using KNIME Deep Learning - Kerasintegration.We want to train a model to distinguish cats and dogs on images. Train classification layer.Read in preprocessedimages from Workflow 01_Preprocessing.Apply trainedmodelwith Keras.Join prediction withoriginal class label.Score the model.Create simple CNN.Partition the datainto training andtest set.Unify RowIDs.Turn probabilitiesto class labels.Turn 'Cat' into 0 and 'Dog' into 1. DL PythonNetwork Learner Table Reader(deprecated) DL Python NetworkExecutor Joiner (deprecated) Scorer (deprecated) DL PythonNetwork Creator Partitioning RowID Rule Engine Rule Engine KNIME Deep Learning - Classify Cats and Dogs In this series of workflows we want to demonstrate how to solve animage classification problem using KNIME Deep Learning - Kerasintegration.We want to train a model to distinguish cats and dogs on images. Train classification layer.Read in preprocessedimages from Workflow 01_Preprocessing.Apply trainedmodelwith Keras.Join prediction withoriginal class label.Score the model.Create simple CNN.Partition the datainto training andtest set.Unify RowIDs.Turn probabilitiesto class labels.Turn 'Cat' into 0 and 'Dog' into 1.DL PythonNetwork Learner Table Reader(deprecated) DL Python NetworkExecutor Joiner (deprecated) Scorer (deprecated) DL PythonNetwork Creator Partitioning RowID Rule Engine Rule Engine

Nodes

Extensions

Links