Scaled Dot Product attention error
AliOsm opened this issue · comments
Ali Hamdi Ali Fadel commented
When applying scaled dot product attention is gives the following error:
TypeError: Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.
Any idea?
CyberZHG commented
A list of three tensors is needed as input. I've made an update and single input is supported now.
Ali Hamdi Ali Fadel commented
It is works now, but unfortunately, either ScaledDotProduct, SeqSelfAttention or SeqWeightedAttention did not make any improvement in text classification or sequence labeling tasks, any idea?
stale commented
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.