Testing trained model

[benliu961]

Hello,

I have a trained model. How would I get predictions and testing accuracy using a test dataset?

Thank you!

[vondele]

That would be the validation loss, but generally we test newly trained nets by playing games with run_games.py. easy_train.py shows how this can be done. Nets that test well locally can be tested on fishtest as well.

[benliu961]

If I fine tuned the model so that it doesn't predict board evaluations anymore, how would I test it?

[Blimpyway]

What does it predict?

[benliu961]

It predicts a value that I have defined as Value of Computation. Its just some value between 0 and 1

[Sopel97]

Unless this value represents some truth there is no way to test other than play games.

[benliu961]

Is there no way to test it via tensorflow?

[Sopel97]

best you can do is look at loss