How to integrate Keras using Conda and Python Using Knime

[mlauber71]

@sophia_09 you might want to read the official guide

https://docs.knime.com/latest/deep_learning_installation_guide/index.html#_introduction

Then you should set up Miniconda and understand how knime and python work together

Meta Collection about KNIME and Python – mlauber71

Then you could take a look at these examples and try if this does work for you. Please note knime and Keras will need very specific versions to work together - the environment propagation should take care of that:

AttributeError: module ‘keras.optimizers’ has no attribute ‘Adam’

@akhtarameen as it happens I just have collected some example how to set up Keras and Tensor Flow 2 (for classification tasks) with the help of the Conda Environment propagation. If you have a working Miniconda or Anaconda environment configured in KNIME you should be able to just use the propagation and get a working deep learning setup. You would then have to carefully check and plan what you want to d with the setup and what architecture you want to use. [image] [image] The setup in …

You can also follow the discussion in this thread

"An error occured during training of the Keras deep learning network" when using KNIME

@akhtarameen I have adapted the example and added a propagation myself and successfully run it on a Windows machine and it seems to work (hope @Kathrin does not mind). The propagation would have to be pre-run in order to work (so best you use my example). You might have to allow it to create a new Python environment. I initially did find the propagation concept a little confusing to be honest. [image] [image] Then you might want to include more information about your system and what the …