Closed da03 closed 3 years ago
Some tasks (like imdb) do not have validation sets, so the results on "val" are tests. On other tasks, you the test sets are usually also produced as a tensorflow dataset object. So you may simply replace "val" with "test" in the main training script or copy the eval loop once more to eval on test.
Should we expect evaluation scripts/notebooks to be added soon?
See #8 for a fix.
@cifkao, the test_only is giving very low accuracy on listops, while the validation accuracy during training is much higher. Any idea why?
This might be a dumb question, but it seems that there's only a train.py which trains and prints validation stats. How to test the model to get numbers comparable to accuracy numbers in the table?