Open STRATZ-Ken opened 2 years ago
This was solved by enabling eager on the model, and not using accuracy
but binary_accuracy
.
I'm having the same problem training a regression model - fails on the third round. Using tf 2.9.1 so eager is enabled by default, and I tried using both 'mse' and 'val_mse' and both fail.
seems to be related to the num_initial_points parameter because after I change to 4 from the default of 2 it fails after 4 instead of 2
@jessegmeyerlab Are you getting the same error message of AttributeError: 'Tensor' object has no attribute 'numpy'
?
@jessegmeyerlab Are you getting the same error message of
AttributeError: 'Tensor' object has no attribute 'numpy'
?
Yes
@jessegmeyerlab It seems an important bug. Would you share a code snippet for us to reproduce the error? Thanks!
I do use a custom loss function. Not sure if that matters, saw a few posts on it.