Closed harbecke closed 5 years ago
I support the change but I would be very interested to see if the VerticalWrapperModel
actually improves the performance on e.g. 7x7.
do you have a specific test in mind or should i just train a model for 300 epochs without the VerticalWrapperModel
and we compare?
That is exactly what I had in mind. Would be great to have some of the comparison models in reference_models.json
@cleeff @simonant suggestion:
in the first version the tensor gets transposed and the channels are switched after a move, in the second version it gets transposed and multiplied with (-1)
i'll test which of these versions works better. or do you see pitfalls?
Sounds sane.
board_tensor
has three channels, where one or two should suffice. the tensor should be transposed after a player made a move, such that the model only plays the board in one direction. This removes the need forVerticalWrapperModel