ValueError from NASNet function

[dgmp88]

edited - thought this was related to include_top, but seems not

e.g.

from nasnet import NASNet
n = NASNet()

gives

ValueError: Operands could not be broadcast together with shapes (331, 331, 168) (331, 331, 96)

I guess this is the same as this, however I'm using tensorflow 1.6

Thanks for the extremely useful work! :)

[dgmp88]

It works fine if I just use NASNetLarge or NASNetSmall directly - is it just that the defaults for the NASNet function don't work?

[titu1994]

NASNet-A is extremely picky about it's hyperparameter combinations. Try matching the parameters from the prebuilt models in the NASNet function.

The prebut models only wrap around the actual NASNet function which builds the model.