Hi,
I built ANN model in Keras (2 hiden layers of 32 nodes) in R learner. It evaluates perfectly in R Learner.
> print(knime.model)
Model
________________________________________________________________________________
Layer (type) Output Shape Param #
================================================================================
dense_1 (Dense) (None, 32) 1152
________________________________________________________________________________
dropout_1 (Dropout) (None, 32) 0
________________________________________________________________________________
dense_2 (Dense) (None, 32) 1056
________________________________________________________________________________
dropout_2 (Dropout) (None, 32) 0
________________________________________________________________________________
dense_3 (Dense) (None, 1) 33
================================================================================
Total params: 2,241
Trainable params: 2,241
Non-trainable params: 0
__________________________
But when I pass it to R predictor, knime.model shows -
> print(knime.model)
<pointer: 0x0>
What can be possible issues?
Regards,
Nikhil