I further inspected my code. If I removed the bidirectional layer, the GPU computing speed returned to normal (keras 3)
for the activation function, I saw posts that said only using 'tanh' will enable CuDNNLSTM, which is faster than lstm.
JasonzzZ
Users receive reputation points by contributing quality content to the forums.
Posts include post and replies published on the forums.
Post authors can mark replies as Accepted to indicate successful solutions.
Apple Developer Forums admins can mark replies as Apple Recommended to indicate an approved solution