A little help...

[xino1010]

Dear @off99555
I am interested in applying the permutational layer to my model that consists of:
30 individual features for element A, 30 individual features for elment B and 9 common characteristics.

I would like to train my model using permutational_layer.py

Could you guide me using you project?

Regards

[offchan42]

For now, you can download the layers.py and permutational_layer.py into your folder and import permutational_layer to use it.
If you want it without much details, use PermutationalModule. But if you want more fine-tuned options, use the individual functions inside that file and compose them.
The example is in the file itself.
To know how to use it, I suggest you run python permutational_layer.py, and look at the bottom section of the code. Compare the result line by line from the code to the output, try to make sense of it and you should learn better how to use the module.

[offchan42]

You should see that I use the function repeat_layers a lot. It's the function I wrote myself.
It's simply creating a list of same layers. E.g. when you want 2 dense layers with 16 neurons and 4 neurons respectively, you would write:
repeat_layers(Dense, [16, 4], activation="relu")

You can also write [Dense(16, activation='relu'), Dense(4, activation='relu')] for a more verbose way.