Mikko Kotila

I looked into this briefly, and noted conv2d takes in a 4d input (conv2d a 3d). So this lead me to think that perhaps KerasModel() could diverge into several (e.g....

@saichandrareddy1 I don't see why that would be a problem, but this ticket is unrelated. Feel free to open new issue if you like.

I think the AutoML capabilities will end up in its own repository eventually.

I guess one simple way to allow a broader ability to have custom labels for parameters would be to support using a tuple as well as just values. So then...

Good catch. So it shall be.

Getting to this now. It's a bit bigger job because it introduces a different way of handling params (the label and the value needs to be different) so will have...

What do you think if we just instead make it so that if the format is `dict` then the label will used. That way it supports any arbitrary codes.

Good catch. I guess the simplest way to do this would be to check the ~~weight~~ shape in evaluate (which is in any case useful for integrity) and the throw...

Related with this issue, what do you think should be the behavior? I think it's generally good to avoid "magics" unless it is under autom8 which is all about it....

Makes total sense, will be added :)