@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.
The setup in the KNIME preferences would look something like this. You can generate a deep learning environment here or try to let the Conda environment propagation do the job for you once you have a basic Miniconda running (regardless of the Python version).
The same thing should also work with Tensor Flow:
If you just want (some) Deep Learning without configurations and Python you can just force H2O.ai AutoML to do the job 
